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

    Neuronpedia

    INDEX
    Explanations

    supervised

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     value
    -0.07
     culture
    -0.07
    .CreateTable
    -0.07
     inner
    -0.07
    땃
    -0.07
    _CLASS
    -0.07
    localctx
    -0.06
    טייל
    -0.06
     Imagine
    -0.06
    Add
    -0.06
    POSITIVE LOGITS
    _u
    0.07
    บางคน
    0.07
    -established
    0.07
    _RGBA
    0.07
    就必须
    0.07
    前一天
    0.07
     никогда
    0.07
    早已
    0.07
    无需
    0.06
     supervised
    0.06
    Act Density 0.002%

    No Known Activations