Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    replace

    np_max-act · gemini-2.0-flash

    function definitions and associated comments in code, specifically looking for decorators, module information, or soft declarations at the beginning of scripts.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron activates on occurrences of the string “replace,” i.e. calls to a replace operation.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    -w
    -0.06
     requested
    -0.06
    Compatible
    -0.06
    едагог
    -0.06
     beep
    -0.06
    bitmap
    -0.06
    ecimal
    -0.06
    .tmp
    -0.06
     ==========
    -0.06
     σημαν
    -0.06
    POSITIVE LOGITS
    replaceAll
    0.08
     oxidation
    0.07
    GLE
    0.07
     accidentally
    0.07
    gle
    0.07
     будинку
    0.06
    .replaceAll
    0.06
     Crushers
    0.06
    APER
    0.06
     Puppy
    0.06
    Act Density 0.006%

    No Known Activations