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

    Neuronpedia

    INDEX
    Explanations

    function argument descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     prise
    0.50
     "."
    0.43
    ק
    0.43
     ź
    0.43
    ุ
    0.42
    𝓹
    0.42
    ném
    0.42
     প্রাধ
    0.41
     ג
    0.41
     arrec
    0.41
    POSITIVE LOGITS
    (/[
    0.38
    compressible
    0.37
    Tutorial
    0.37
    agnetic
    0.37
     그렇게
    0.37
     permitan
    0.36
     Tutorials
    0.36
    哲学
    0.36
    riting
    0.35
    Exact
    0.35
    Act Density 0.041%

    No Known Activations