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

    Neuronpedia

    INDEX
    Explanations

    U.S. patents

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     energetic
    -0.07
    이나
    -0.07
    (logits
    -0.07
     אומר
    -0.07
     ES
    -0.07
     있기
    -0.07
     станет
    -0.07
    แขน
    -0.07
    /Images
    -0.07
     השירות
    -0.06
    POSITIVE LOGITS
     зад
    0.08
    넖
    0.07
    rov
    0.07
    elerik
    0.07
     detective
    0.07
    自主研发
    0.07
    _advance
    0.07
     hesabı
    0.06
    eldorf
    0.06
    .Exp
    0.06
    Act Density 0.013%

    No Known Activations