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

    Neuronpedia

    INDEX
    Explanations

    repositories

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    uite
    -0.07
    dto
    -0.07
    -0.06
    測
    -0.06
    ‌پ
    -0.06
     Destiny
    -0.06
    -0.06
    項目
    -0.06
     relatively
    -0.06
    alarında
    -0.06
    POSITIVE LOGITS
    Aceptar
    0.07
     Lessons
    0.07
     �
    0.07
    Toronto
    0.06
    .PIPE
    0.06
    NSDictionary
    0.06
     orally
    0.06
    امین
    0.06
    sans
    0.06
    Cancelar
    0.06
    Act Density 0.002%

    No Known Activations