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

    Neuronpedia

    INDEX
    Explanations

    skills and practices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     democr
    0.42
    గల
    0.41
    ייט
    0.40
    ITA
    0.37
    cyte
    0.37
    iş
    0.36
     dashes
    0.36
     menace
    0.35
    парат
    0.35
    陏
    0.35
    POSITIVE LOGITS
     outras
    0.38
     ইন্স
    0.38
    otherapy
    0.37
     SUBTOTAL
    0.37
     Dex
    0.35
    StopTime
    0.35
     DELIVERY
    0.35
     башка
    0.35
    ຕ
    0.35
    ┓
    0.35
    Act Density 0.000%

    No Known Activations