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

    Neuronpedia

    INDEX
    Explanations

    present

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -flag
    -0.08
    栎
    -0.07
     Mitar
    -0.07
     Hogan
    -0.07
     mata
    -0.07
    (fr
    -0.07
    ثر
    -0.07
    帰
    -0.07
     spiel
    -0.07
    qed
    -0.06
    POSITIVE LOGITS
     essay
    0.07
     Clock
    0.07
    廉
    0.06
     progressed
    0.06
     הנוכחי
    0.06
    星星
    0.06
    lock
    0.06
     page
    0.06
     system
    0.06
    古今
    0.06
    Act Density 0.002%

    No Known Activations