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

    Neuronpedia

    INDEX
    Explanations

    =

    np_max-act · gemini-2.0-flash

    This neuron fires on floating‐point numeric literals (numbers containing a decimal point) in the code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .form
    -0.07
     노
    -0.07
    اک
    -0.07
    (Util
    -0.07
    (jsonObject
    -0.07
     buff
    -0.07
     encour
    -0.06
     strive
    -0.06
    List
    -0.06
    _PIPE
    -0.06
    POSITIVE LOGITS
     staveb
    0.06
    ิญ
    0.06
     preferredStyle
    0.06
    SKI
    0.06
    шиб
    0.06
    каз
    0.06
    $PostalCodesNL
    0.06
    шая
    0.06
     plusieurs
    0.06
    .timeScale
    0.06
    Act Density 0.004%

    No Known Activations