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

    Neuronpedia

    INDEX
    Explanations

    Jekyll

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    W
    -0.08
    One
    -0.07
     hesitation
    -0.07
     trees
    -0.06
    Four
    -0.06
    Rock
    -0.06
    master
    -0.06
    лена
    -0.06
    职
    -0.06
     fb
    -0.06
    POSITIVE LOGITS
    NSNotificationCenter
    0.07
    (sin
    0.06
    talya
    0.06
    StorageSync
    0.06
    _pen
    0.06
     makeover
    0.06
    [num
    0.06
     Johann
    0.06
    긴
    0.06
     معماری
    0.06
    Act Density 0.034%

    No Known Activations