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

    Neuronpedia

    INDEX
    Explanations

    by [teams/the/a/humans]

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     क्वेश्चन
    0.50
     लिखी
    0.43
     json
    0.42
     लिखे
    0.41
    探讨
    0.41
     например
    0.40
     കൂടുതൽ
    0.40
     Browse
    0.40
    Ь
    0.40
    诱
    0.39
    POSITIVE LOGITS
    isocyanate
    0.41
     appliquer
    0.41
    ሙሉ
    0.40
    WindowConstants
    0.39
     nostra
    0.39
    鍮
    0.38
     Aktual
    0.38
    NDAY
    0.38
    溸
    0.38
    நாய
    0.37
    Act Density 0.001%

    No Known Activations