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

    Neuronpedia

    INDEX
    Explanations

    Calculation of scores

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    cac
    -0.07
    .nodeType
    -0.06
     پای
    -0.06
    こう
    -0.06
     ساز
    -0.06
    ,res
    -0.06
     Mash
    -0.06
    仕事
    -0.06
    _PRIORITY
    -0.06
     builds
    -0.06
    POSITIVE LOGITS
    bert
    0.08
    lexible
    0.06
     ）↵
    0.06
     rampant
    0.06
     Iowa
    0.06
     &↵
    0.06
    ，《
    0.06
    alchemy
    0.06
     통해
    0.06
    (!$
    0.06
    Act Density 0.052%

    No Known Activations