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

    Neuronpedia

    INDEX
    Explanations

    tf

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    新增
    -0.07
    .isValid
    -0.07
     Auschwitz
    -0.07
    CallCheck
    -0.07
    ultz
    -0.06
    MainActivity
    -0.06
    pecially
    -0.06
    '''
    -0.06
     businessmen
    -0.06
     minority
    -0.06
    POSITIVE LOGITS
     tf
    0.11
    =tf
    0.07
     IP
    0.07
    _tf
    0.07
    ff
    0.06
     F
    0.06
     sg
    0.06
     TF
    0.06
     psychic
    0.06
    fp
    0.06
    Act Density 0.003%

    No Known Activations