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
     mik
    -0.06
     tod
    -0.06
    。\
    -0.06
     Lar
    -0.06
     ))
    -0.06
    Compatibility
    -0.06
    ۵۰
    -0.06
            ↵        ↵        ↵
    -0.06
     广
    -0.06
     ابتد
    -0.06
    POSITIVE LOGITS
    사랑
    0.07
    rible
    0.07
     nuis
    0.06
    řeh
    0.06
    wins
    0.06
    ş
    0.06
    夏
    0.06
     vs
    0.06
     keeping
    0.06
    ậc
    0.06
    Act Density 0.097%

    No Known Activations