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

    Neuronpedia

    INDEX
    Explanations

    numeric/symbolic code and words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    s
    1.18
    oretically
    1.14
    ️
    1.05
    er
    1.03
    ly
    1.00
    ে
    0.99
    xiety
    0.94
    ed
    0.93
    ي
    0.91
    ️⃣
    0.90
    POSITIVE LOGITS
    1
    0.68
    2
    0.67
    éléments
    0.65
    $(
    0.64
    3
    0.62
    $-
    0.62
    foreach
    0.61
    przy
    0.60
    indeed
    0.60
    ρυθ
    0.59
    Act Density 0.550%

    No Known Activations