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

    Neuronpedia

    INDEX
    Explanations

    {

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Voy
    -0.07
    -0.07
    (station
    -0.07
    步骤
    -0.07
    .house
    -0.07
     Defendant
    -0.07
    .za
    -0.07
    .genre
    -0.06
     veículo
    -0.06
     ,,
    -0.06
    POSITIVE LOGITS
    ダメ
    0.07
     discret
    0.07
     sống
    0.07
    alog
    0.07
     иност
    0.07
    -establish
    0.07
    otten
    0.07
     der
    0.06
    强大的
    0.06
     optim
    0.06
    Act Density 0.040%

    No Known Activations