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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash

    This neuron detects occurrences of “set” in method names—that is, it fires on setter method declarations.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _Create
    -0.08
    |array
    -0.08
    .Enter
    -0.07
    esy
    -0.07
    .heading
    -0.06
     Truly
    -0.06
     Drink
    -0.06
    .with
    -0.06
     кир
    -0.06
    _POP
    -0.06
    POSITIVE LOGITS
    -lined
    0.07
     setResult
    0.06
     Proj
    0.06
    electron
    0.06
     Murray
    0.06
    olle
    0.06
     tudo
    0.06
    ($(".
    0.06
     이벤트
    0.06
    도로
    0.06
    Act Density 0.023%

    No Known Activations