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

    Neuronpedia

    INDEX
    Explanations

    ="

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (datas
    -0.07
    _ds
    -0.07
    mtree
    -0.07
     Gesch
    -0.07
     história
    -0.06
     smells
    -0.06
     Accent
    -0.06
    _PH
    -0.06
     dear
    -0.06
     aValue
    -0.06
    POSITIVE LOGITS
    宏
    0.06
    итуа
    0.06
    �
    0.06
    favicon
    0.06
    .options
    0.06
     turnout
    0.06
     cars
    0.06
    webpack
    0.06
     preseason
    0.06
    ानत
    0.06
    Act Density 0.008%

    No Known Activations