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

    Neuronpedia

    INDEX
    Explanations

    power-ups in games

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     صفحات
    -0.08
     hawa
    -0.08
     ghar
    -0.08
     удовлетвор
    -0.08
     anhand
    -0.07
     עם
    -0.07
     incl
    -0.07
    �
    -0.07
     latela
    -0.07
     দূ
    -0.07
    POSITIVE LOGITS
     Activate
    0.11
    .activate
    0.11
     activates
    0.11
     pausa
    0.09
    暂停
    0.09
     occasionally
    0.09
     Activation
    0.09
     activate
    0.09
     activating
    0.09
     activated
    0.09
    Act Density 0.047%

    No Known Activations