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

    Neuronpedia

    INDEX
    Explanations

    sports news articles

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (userInfo
    -0.07
     undergrad
    -0.06
     Wisconsin
    -0.06
    ぶ
    -0.06
     Krishna
    -0.06
    心
    -0.06
    .Ticks
    -0.06
     Facilities
    -0.06
     Superman
    -0.06
    tpl
    -0.05
    POSITIVE LOGITS
    atik
    0.07
    637
    0.07
    LError
    0.07
    (bool
    0.07
    xfd
    0.06
    imeo
    0.06
    anness
    0.06
     itir
    0.06
     proclamation
    0.06
    (Cell
    0.06
    Act Density 0.006%

    No Known Activations