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

    Neuronpedia

    INDEX
    Explanations

    return biz_id regarding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    (){
    -0.84
     empezar
    -0.83
    tojas
    -0.83
    ☣
    -0.83
    digde
    -0.82
    +$
    -0.82
    CPtr
    -0.81
    reiche
    -0.81
    IfNeeded
    -0.79
    ','',
    -0.79
    POSITIVE LOGITS
    return
    1.91
     return
    1.25
     returns
    1.06
    肿瘤
    0.90
     not
    0.75
     retVal
    0.73
     없
    0.72
    到底是
    0.71
     said
    0.71
     basic
    0.71
    Act Density 0.001%

    No Known Activations