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

    Neuronpedia

    INDEX
    Explanations

    Thorough/complete

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Construction
    -0.07
    _box
    -0.07
     seemingly
    -0.07
    .LocalDateTime
    -0.06
    IDX
    -0.06
    _NOTIFICATION
    -0.06
     customary
    -0.06
     oranı
    -0.06
     identical
    -0.06
    =@"
    -0.06
    POSITIVE LOGITS
     Michele
    0.07
     війсь
    0.07
    leniyor
    0.06
     GREAT
    0.06
     MMO
    0.06
     приступ
    0.06
     дир
    0.06
     PR
    0.06
    ısır
    0.06
     пос
    0.06
    Act Density 0.080%

    No Known Activations