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

    Neuronpedia

    INDEX
    Explanations

    mathematical or technical explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    s
    0.91
    0.85
     nhà
    0.80
     danh
    0.78
    ﮔ
    0.77
     cuatro
    0.76
     värld
    0.74
     पांच
    0.74
     buckle
    0.73
     veik
    0.73
    POSITIVE LOGITS
    ून
    1.09
    ний
    1.04
     (\"
    1.03
    ⃣
    1.02
     (
    0.99
    ர்
    0.97
    of
    0.96
    м
    0.94
    ありません
    0.93
    に
    0.93
    Act Density 0.382%

    No Known Activations