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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ING
    0.46
    ة
    0.33
    ८
    0.33
    ९
    0.31
    ing
    0.31
    ۹
    0.29
    <unused28>
    0.28
    لي
    0.28
    тие
    0.27
    Emitter
    0.27
    POSITIVE LOGITS
    st
    0.48
    1
    0.45
    к
    0.41
    z
    0.41
    i
    0.40
    k
    0.38
    ل
    0.38
     Caucasus
    0.34
    １
    0.34
    ル
    0.34
    Act Density 0.374%

    No Known Activations