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

    Neuronpedia

    INDEX
    Explanations

    double compounds and phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ک
    1.49
    א
    1.29
     a
    1.28
    ο
    1.21
    та
    1.19
    ט
    1.16
    }.
    1.14
    }'
    1.14
    ק
    1.13
    ի
    1.13
    POSITIVE LOGITS
     Double
    1.13
    는
    1.05
    是
    1.04
     double
    0.94
    是通过
    0.83
    h
    0.82
    是用
    0.82
    是为了
    0.80
    েল
    0.79
    로
    0.78
    Act Density 0.008%

    No Known Activations