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

    Neuronpedia

    INDEX
    Explanations

    as

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    andro
    -0.07
     mercury
    -0.07
    مت
    -0.07
     مد
    -0.07
     ---------------------------------------------------------------------------↵
    -0.07
     itertools
    -0.07
     prohibit
    -0.07
    秸秆
    -0.06
    $time
    -0.06
     downs
    -0.06
    POSITIVE LOGITS
    _contr
    0.08
     upright
    0.08
     asc
    0.07
     sebuah
    0.07
    液晶
    0.07
    _ASYNC
    0.07
     circuits
    0.07
     curing
    0.07
    Inverse
    0.07
    Lists
    0.07
    Act Density 0.203%

    No Known Activations