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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    inc
    -0.06
     bomber
    -0.06
    ことを
    -0.06
    mızı
    -0.06
    idan
    -0.06
     eats
    -0.06
    ayd
    -0.06
    uvo
    -0.06
    seven
    -0.06
    compass
    -0.06
    POSITIVE LOGITS
     filt
    0.07
     insider
    0.06
     omit
    0.06
    .dc
    0.06
     �
    0.06
    网刊下载次数
    0.06
     neurop
    0.06
    regor
    0.06
    _dc
    0.06
     давно
    0.06
    Act Density 0.124%

    No Known Activations