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

    Neuronpedia

    INDEX
    Explanations

    resize images

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ה
    0.95
    s
    0.87
    ק
    0.86
     responsibility
    0.83
    ંજ
    0.80
    น
    0.78
    ט
    0.77
    ده
    0.74
     momentum
    0.73
     signal
    0.72
    POSITIVE LOGITS
    い
    1.21
    いずれ
    1.13
    ➢
    1.05
    いっぱい
    1.02
    ➺
    0.98
    いき
    0.97
     ఆధ్యా
    0.96
    emplate
    0.94
    goers
    0.93
     ඕ
    0.93
    Act Density 0.000%

    No Known Activations