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

    Neuronpedia

    INDEX
    Explanations

    Code diffs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    有名
    -0.08
     Frid
    -0.07
     perse
    -0.07
     geliş
    -0.07
     Ventura
    -0.07
    鳀
    -0.07
    퍄
    -0.07
     lit
    -0.07
     פוס
    -0.07
    橞
    -0.06
    POSITIVE LOGITS
    sharp
    0.07
     �
    0.07
    unkt
    0.07
     Tuple
    0.07
    زة
    0.07
    owego
    0.06
    /w
    0.06
     מבלי
    0.06
    ść
    0.06
    iga
    0.06
    Act Density 0.001%

    No Known Activations