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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Malta
    -0.07
    луч
    -0.07
    poč
    -0.06
    来了
    -0.06
     Волод
    -0.06
     �
    -0.06
    �
    -0.06
    Pu
    -0.06
    uí
    -0.06
    .GONE
    -0.06
    POSITIVE LOGITS
    shire
    0.08
     wasn
    0.06
    SELL
    0.06
     ge
    0.06
     woods
    0.06
     kişinin
    0.06
     aren
    0.06
     Become
    0.06
     missed
    0.06
    Cursor
    0.06
    Act Density 0.019%

    No Known Activations