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

    Neuronpedia

    INDEX
    Explanations

    severity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .urlencoded
    -0.08
    학년도
    -0.07
    	con
    -0.07
     autoComplete
    -0.07
    amin
    -0.06
     breastfeeding
    -0.06
    )test
    -0.06
     være
    -0.06
    بول
    -0.06
    ۴
    -0.06
    POSITIVE LOGITS
     severity
    0.08
     armor
    0.07
     Pav
    0.07
    _ANY
    0.07
     그래서
    0.07
    uity
    0.07
    .StringVar
    0.07
     fieldName
    0.06
     Ord
    0.06
    Gesture
    0.06
    Act Density 0.010%

    No Known Activations