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

    Neuronpedia

    INDEX
    Explanations

    code and configuration tags

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    羕
    -1.63
    ösen
    -1.54
    眛
    -1.52
    嘥
    -1.46
    瘊
    -1.45
    dámské
    -1.45
    maillot
    -1.44
    要点
    -1.41
    訁
    -1.39
    marzo
    -1.38
    POSITIVE LOGITS
    ).
    1.86
    else
    1.69
    ".
    1.68
     $
    1.62
    private
    1.61
    可能会
    1.55
    all
    1.55
    ка
    1.53
    ",
    1.51
    D
    1.46
    Act Density 0.011%

    No Known Activations