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

    Neuronpedia

    INDEX
    Explanations

    class and function definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Yeah
    0.79
    Yep
    0.76
    Yeah
    0.74
     Ако
    0.73
    이랑
    0.72
     glad
    0.71
    Ờ
    0.71
    的发展
    0.71
    嘛
    0.70
    allax
    0.70
    POSITIVE LOGITS
     [,
    1.04
    [,
    1.02
    readonly
    0.96
    ?:
    0.96
    ?,
    0.94
     readonly
    0.93
    /**
    0.84
     ?,
    0.83
    :,
    0.82
    ')?.
    0.79
    Act Density 0.148%

    No Known Activations