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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ѫ
    -0.07
    闪过
    -0.07
    uuid
    -0.07
    Invalid
    -0.07
     rewarded
    -0.06
    嚎
    -0.06
    _formatted
    -0.06
    inv
    -0.06
    /generated
    -0.06
    悼
    -0.06
    POSITIVE LOGITS
     Armenia
    0.07
     aç
    0.07
     ISO
    0.07
     diversas
    0.07
     plata
    0.07
     Wheat
    0.07
     abolition
    0.07
    ⼥
    0.07
     administration
    0.06
     agosto
    0.06
    Act Density 0.056%

    No Known Activations