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

    Neuronpedia

    INDEX
    Explanations

    been around or through

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𝗵
    0.34
    pOt
    0.29
    πομπ
    0.29
    𝐡
    0.28
     बाउ
    0.28
    𝓈
    0.28
    意義
    0.27
    стное
    0.27
    żs
    0.27
     છીએ
    0.27
    POSITIVE LOGITS
    Estimated
    0.37
    estimated
    0.31
     Typical
    0.30
    typical
    0.29
    Typical
    0.29
    argon
    0.28
    推定
    0.28
     Typically
    0.27
    size
    0.27
    length
    0.27
    Act Density 0.000%

    No Known Activations