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

    Neuronpedia

    INDEX
    Explanations

    paced

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hoof
    -0.07
     quint
    -0.06
     Blo
    -0.06
     Apartment
    -0.06
     supp
    -0.06
    Gets
    -0.06
     examiner
    -0.06
    促
    -0.06
    ,h
    -0.06
    :num
    -0.06
    POSITIVE LOGITS
    Fecha
    0.07
     بیماری
    0.07
    valor
    0.07
     đạo
    0.06
     {↵
    0.06
    (getClass
    0.06
    луш
    0.06
     jehož
    0.06
    퇴
    0.06
    _LOG
    0.06
    Act Density 0.009%

    No Known Activations