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

    Neuronpedia

    INDEX
    Explanations

    resetting devices

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    140
    -0.07
     larg
    -0.07
     nose
    -0.06
     ----------------------------------------------------------------
    -0.06
     unh
    -0.06
    _languages
    -0.06
     NavParams
    -0.06
     catal
    -0.06
    /'+
    -0.06
    acellular
    -0.06
    POSITIVE LOGITS
    (userName
    0.07
     tranny
    0.06
     จะ
    0.06
    ?(
    0.06
    _station
    0.06
    ANTI
    0.06
    _bytes
    0.06
    认识
    0.06
    وجد
    0.06
    .charCodeAt
    0.06
    Act Density 0.019%

    No Known Activations