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

    Neuronpedia

    INDEX
    Explanations

    HTML tags and links

    np_acts-logits-general · gemini-2.5-flash-lite

    html and javascript tags

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    D
    1.15
    G
    1.14
    F
    1.13
    E
    1.12
    Н
    1.12
    N
    1.10
    -
    1.09
    ン
    1.02
    ↵↵
    0.99
    া
    0.94
    POSITIVE LOGITS
    </
    1.04
    da
    0.96
    ية
    0.95
    dır
    0.93
    ut
    0.91
    é
    0.89
    ي
    0.88
    ur
    0.85
     as
    0.80
    deling
    0.80
    Act Density 0.000%

    No Known Activations