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

    Neuronpedia

    INDEX
    Explanations

    Dosage

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    alan
    -0.06
     writes
    -0.06
    يا
    -0.06
    75
    -0.06
    Assignable
    -0.06
    てい
    -0.06
     gamble
    -0.06
    alars
    -0.06
     Licence
    -0.06
    一定
    -0.06
    POSITIVE LOGITS
    \Security
    0.07
    glich
    0.07
    nement
    0.06
     نزد
    0.06
     فرم
    0.06
     prt
    0.06
    imshow
    0.06
     Hlav
    0.06
     Za
    0.06
    ตลาด
    0.06
    Act Density 0.013%

    No Known Activations