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

    Neuronpedia

    INDEX
    Explanations

    npm packages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    l
    1.47
    ם
    1.23
    k
    1.23
    SMITH
    1.12
    ا
    1.11
    ı
    1.09
    ك
    1.07
    ervice
    1.06
    سور
    1.05
    /******/
    1.04
    POSITIVE LOGITS
    া
    1.38
    唑
    1.23
    ාවිත
    1.20
    ，「
    1.16
    ון
    1.14
     Tris
    1.13
    ари
    1.09
     bleue
    1.05
    ়
    1.04
    ？
    1.04
    Act Density 0.004%

    No Known Activations