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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    шили
    -0.08
     Dw
    -0.07
    sten
    -0.07
    718
    -0.07
     WA
    -0.07
    (url
    -0.06
     phức
    -0.06
     instance
    -0.06
    ライ
    -0.06
     Dun
    -0.06
    POSITIVE LOGITS
    _translation
    0.07
    _span
    0.07
    altar
    0.07
    aille
    0.06
    مة
    0.06
     riv
    0.06
     ante
    0.06
     abrasive
    0.06
    hora
    0.06
    YNC
    0.06
    Act Density 0.021%

    No Known Activations