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

    Neuronpedia

    INDEX
    Explanations

    factor

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    portlet
    -0.07
    KNOWN
    -0.07
    764
    -0.06
     sortie
    -0.06
    ouce
    -0.06
     Duch
    -0.06
    ิกายน
    -0.06
    هدف
    -0.06
    bc
    -0.06
    ########
    -0.06
    POSITIVE LOGITS
     strav
    0.06
     distributes
    0.06
     effective
    0.06
    ФЛ
    0.06
     katı
    0.06
    Kom
    0.06
    /graphql
    0.06
     inspect
    0.06
    .Popen
    0.06
    _STMT
    0.06
    Act Density 0.001%

    No Known Activations