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
     상담
    -0.07
    173
    -0.07
    cribes
    -0.07
    ाऊ
    -0.07
     basic
    -0.06
     सल
    -0.06
     abusing
    -0.06
     dever
    -0.06
    _bool
    -0.06
    श
    -0.06
    POSITIVE LOGITS
    alarm
    0.06
    김
    0.06
    Il
    0.06
    ////////////////
    0.06
    kj
    0.06
    --↵
    0.06
     //////////////////
    0.06
    bab
    0.06
    .av
    0.06
    ้วย
    0.06
    Act Density 0.025%

    No Known Activations