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

    Neuronpedia

    INDEX
    Explanations

    Parentheses

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ulations
    -0.07
     Baum
    -0.07
    abcdefghijklmnopqrstuvwxyz
    -0.07
    巫
    -0.07
     deliberately
    -0.07
    _handlers
    -0.07
    wen
    -0.07
    amber
    -0.07
    ohana
    -0.07
    ခ
    -0.06
    POSITIVE LOGITS
    𝚝
    0.10
    Ѱ
    0.07
    겯
    0.07
    مواجه
    0.07
     pard
    0.07
     hat
    0.07
    硕士研究
    0.07
    OWER
    0.07
     cực
    0.06
     incorpor
    0.06
    Act Density 0.009%

    No Known Activations