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

    Neuronpedia

    INDEX
    Explanations

    logos

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     معينة
    -0.08
     gjelder
    -0.08
     daring
    -0.08
     الأمن
    -0.07
     стер
    -0.07
    USART
    -0.07
     ويل
    -0.07
    .TEST
    -0.07
     Existe
    -0.07
     Stunde
    -0.07
    POSITIVE LOGITS
     persuasion
    0.10
     appeals
    0.08
     appealing
    0.08
    0.08
     appeal
    0.08
     свидетель
    0.08
     apresent
    0.08
     informative
    0.08
     persu
    0.08
    據
    0.08
    Act Density 0.002%
    No Known Activations