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

    Neuronpedia

    INDEX
    Explanations

    Code/programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     :
    -0.08
     (
    -0.08
     rozší
    -0.07
     elsewhere
    -0.07
    :
    -0.06
    verbatim
    -0.06
     ausge
    -0.06
    _DE
    -0.06
    -0.06
    比赛
    -0.06
    POSITIVE LOGITS
     Truck
    0.06
    zza
    0.06
    zbek
    0.06
    iversity
    0.06
     canned
    0.06
    Interval
    0.06
    کن
    0.06
     Civilization
    0.06
    ês
    0.06
     Серг
    0.06
    Act Density 1.007%

    No Known Activations