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

    Neuronpedia

    INDEX
    Explanations

    code, functions, and data types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Botox
    0.33
    蛲
    0.33
    <unused1019>
    0.33
     वनस्पती
    0.32
     punctatis
    0.32
    🩺
    0.32
     denaturation
    0.30
     लोकप्रियता
    0.30
    🥩
    0.30
    ^{(\
    0.30
    POSITIVE LOGITS
    (
    0.38
    ()),
    0.35
    (),
    0.34
    _
    0.32
    Util
    0.32
    utils
    0.31
    된
    0.31
    ified
    0.30
    ify
    0.29
    AnimationFrame
    0.29
    Act Density 0.043%

    No Known Activations