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

    Neuronpedia

    INDEX
    Explanations

    after very the of this

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    すべき
    0.47
    Grilled
    0.46
    ゼロ
    0.45
     overload
    0.44
    癀
    0.44
    kcal
    0.43
    Exceptionally
    0.43
     இன்
    0.42
    ljanje
    0.42
     overwhel
    0.42
    POSITIVE LOGITS
     L
    0.45
     tế
    0.44
    em
    0.43
     B
    0.43
     con
    0.43
     as
    0.43
    ्राम
    0.43
     V
    0.42
    س
    0.42
     مع
    0.41
    Act Density 0.000%

    No Known Activations