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

    Neuronpedia

    INDEX
    Explanations

    my

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    elong
    -0.07
     такая
    -0.07
    aimassage
    -0.07
     민주
    -0.06
     alcan
    -0.06
    规定
    -0.06
    _pdata
    -0.06
    кта
    -0.06
    شاه
    -0.06
     muối
    -0.06
    POSITIVE LOGITS
     kid
    0.06
     Original
    0.06
     academic
    0.06
    "Our
    0.06
     Given
    0.06
     podcast
    0.06
     Blogger
    0.06
    习
    0.06
    Variable
    0.06
     Sect
    0.06
    Act Density 0.000%

    No Known Activations