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

    Neuronpedia

    INDEX
    Explanations

    Data tables/spreadsheets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     संभ
    -0.08
     разв
    -0.08
    ipheral
    -0.08
     Hyg
    -0.08
    resser
    -0.08
     entertain
    -0.08
     गो
    -0.08
     Toile
    -0.08
     проблему
    -0.07
    耳
    -0.07
    POSITIVE LOGITS
     calculated
    0.11
    计算
    0.11
    Calculated
    0.11
     totals
    0.11
     Gesamt
    0.10
     गण
    0.10
     ગણ
    0.10
     계산
    0.10
     calculations
    0.09
    computed
    0.09
    Act Density 0.054%

    No Known Activations