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

    Neuronpedia

    INDEX
    Explanations

    notarized documents and statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ný
    0.97
    یه
    0.95
    om
    0.92
    I
    0.91
    n
    0.90
    T
    0.88
    M
    0.88
    ظر
    0.87
    k
    0.83
    it
    0.82
    POSITIVE LOGITS
     arabe
    1.09
     özellik
    0.99
     aphids
    0.97
     elevationMap
    0.94
    ন্তর
    0.93
    িন
    0.92
     eenvoud
    0.91
     королев
    0.91
     kwaliteit
    0.90
     semplice
    0.88
    Act Density 0.000%

    No Known Activations