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

    Neuronpedia

    INDEX
    Explanations

    number formatting

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Caught
    0.71
    Ciudad
    0.65
     +#+
    0.61
    B
    0.61
    Traditional
    0.61
    Salon
    0.61
    روف
    0.59
    Ме
    0.59
     Caught
    0.59
     उनसे
    0.57
    POSITIVE LOGITS
     amenable
    0.73
     euthanasia
    0.67
     arson
    0.65
     independence
    0.64
     waterfowl
    0.64
     quiver
    0.63
     recirculation
    0.61
     labyrinth
    0.60
    :.
    0.60
     exerting
    0.59
    Act Density 0.000%

    No Known Activations