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

    Neuronpedia

    INDEX
    Explanations

    say [the digit]

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    最美
    -0.07
    訇
    -0.07
    Maps
    -0.07
    jours
    -0.07
    VAL
    -0.07
     Expect
    -0.07
    楩
    -0.06
     scaleFactor
    -0.06
    ༜
    -0.06
     Osman
    -0.06
    POSITIVE LOGITS
    bat
    0.07
     warehouse
    0.07
    _miss
    0.07
     المحل
    0.06
    躺着
    0.06
    _slots
    0.06
    一点都不
    0.06
    在我看来
    0.06
     sophisticated
    0.06
    不太
    0.06
    Act Density 0.004%

    No Known Activations