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

    Neuronpedia

    INDEX
    Explanations

    GmbH

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     showed
    -0.07
     calendars
    -0.07
     kết
    -0.07
     analý
    -0.06
    .Wrap
    -0.06
     caracteres
    -0.06
    ूज
    -0.06
    Carthy
    -0.06
    lando
    -0.06
     ロ
    -0.06
    POSITIVE LOGITS
    有限公司
    0.07
    escort
    0.07
     geme
    0.07
     серд
    0.06
    iffer
    0.06
     Warranty
    0.06
     بإ
    0.06
     เง
    0.06
    .sym
    0.06
     συνέ
    0.06
    Act Density 0.009%

    No Known Activations