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

    Neuronpedia

    INDEX
    Explanations

    maximum and minimum

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    打电话
    0.41
    忏
    0.41
    䔋
    0.40
    contentType
    0.40
    oldCount
    0.38
     tato
    0.38
     इंद्र
    0.38
     созна
    0.38
    㝒
    0.38
    鸿
    0.38
    POSITIVE LOGITS
     highest
    1.13
     max
    1.09
    max
    1.06
     largest
    1.05
     maxima
    1.03
    Highest
    1.03
    Largest
    1.02
     Highest
    1.02
     maximum
    1.01
    highest
    1.00
    Act Density 0.033%

    No Known Activations