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

    Neuronpedia

    INDEX
    Explanations

    static

    np_max-act · gemini-2.0-flash

    The neuron spotlights numeric literal constants—especially floating‐point values—in source code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    (mon
    -0.06
    051
    -0.06
     fan
    -0.06
     finalist
    -0.06
    _STRUCTURE
    -0.06
     markings
    -0.06
    Bell
    -0.06
    /software
    -0.06
    877
    -0.06
     Variables
    -0.06
    POSITIVE LOGITS
    새
    0.07
     niet
    0.06
    ımızı
    0.06
    ")
    0.06
     ''),↵
    0.06
    *****
↵
    0.06
     �
    0.06
    ався
    0.06
    installer
    0.06
    الت
    0.06
    Act Density 0.001%

    No Known Activations