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

    Neuronpedia

    INDEX
    Explanations

    -repeat

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Bakan
    -0.07
    .JSONException
    -0.07
    .flush
    -0.06
     PROFITS
    -0.06
    Statistic
    -0.06
    .AsyncTask
    -0.06
     ingredients
    -0.06
    MenuItem
    -0.06
    scription
    -0.06
    combination
    -0.06
    POSITIVE LOGITS
    い
    0.07
    TERS
    0.07
     ди
    0.07
     بین
    0.07
     Ferm
    0.07
    ]]↵
    0.06
     teammate
    0.06
    lete
    0.06
    _inverse
    0.06
    ئ
    0.06
    Act Density 0.001%

    No Known Activations