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

    Neuronpedia

    INDEX
    Explanations

    Giving instructions/explanations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     avoir
    -0.07
    (summary
    -0.07
     travail
    -0.06
    '}↵
    -0.06
     utiliza
    -0.06
    金属
    -0.06
     Preview
    -0.06
     gou
    -0.06
     Www
    -0.06
    906
    -0.06
    POSITIVE LOGITS
     MessageBoxButton
    0.08
     инвести
    0.06
    ��
    0.06
    .js
    0.06
     win
    0.06
    /screens
    0.06
     Georgetown
    0.06
     آینده
    0.06
    .seq
    0.06
     fost
    0.06
    Act Density 0.151%

    No Known Activations