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

    Neuronpedia

    INDEX
    Explanations

    positive values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    el
    0.79
    d
    0.71
     Pertama
    0.68
     grep
    0.64
    at
    0.63
    P
    0.63
    et
    0.63
    b
    0.62
     zich
    0.60
    ent
    0.59
    POSITIVE LOGITS
    或
    0.86
    または
    0.85
    <unused1814>
    0.85
    折扣
    0.81
    <unused139>
    0.80
     UIScrollView
    0.79
    timeInterval
    0.79
    𝜇
    0.79
    を指定
    0.78
     (\<
    0.78
    Act Density 0.626%

    No Known Activations