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

    Neuronpedia

    INDEX
    Explanations

    specific concepts and categories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     (
    0.54
     paradox
    0.41
     H
    0.41
     M
    0.39
     Snake
    0.39
     A
    0.38
     P
    0.38
     B
    0.38
     sauté
    0.38
     Python
    0.38
    POSITIVE LOGITS
     və
    0.59
     тощо
    0.59
     и
    0.58
     और
    0.56
     etc
    0.55
    และ
    0.55
     agus
    0.54
     và
    0.52
     आणि
    0.52
     மற்றும்
    0.52
    Act Density 0.191%

    No Known Activations