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

    Neuronpedia

    INDEX
    Explanations

    ipsum

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    overrides
    -0.08
     carr
    -0.07
     sno
    -0.06
     JADX
    -0.06
    success
    -0.06
     motive
    -0.06
    (unique
    -0.06
     sint
    -0.06
     bends
    -0.06
     sortBy
    -0.06
    POSITIVE LOGITS
    Philip
    0.07
     Messiah
    0.07
     insanity
    0.06
    蜘蛛
    0.06
    Trump
    0.06
    fp
    0.06
    Native
    0.06
    اسم
    0.06
    χό
    0.06
    appoint
    0.06
    Act Density 0.001%

    No Known Activations