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

    Neuronpedia

    INDEX
    Explanations

    Code and module definitions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     adjud
    -0.07
     speak
    -0.06
    -tra
    -0.06
     От
    -0.06
    女性
    -0.06
     ماد
    -0.06
     받아
    -0.06
     secular
    -0.06
     هند
    -0.06
    _HAL
    -0.06
    POSITIVE LOGITS
     encore
    0.07
    disposing
    0.07
    setChecked
    0.07
    Normally
    0.06
    $('.
    0.06
     dieta
    0.06
     Наз
    0.06
     고개를
    0.06
    UnitOfWork
    0.06
     Kra
    0.06
    Act Density 0.010%

    No Known Activations