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

    Neuronpedia

    INDEX
    Explanations

    off

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    fold
    0.73
    fiber
    0.72
     جای
    0.70
     obu
    0.70
    ties
    0.69
     have
    0.66
    رین
    0.64
    bait
    0.64
    fibre
    0.64
    convex
    0.63
    POSITIVE LOGITS
     off
    0.95
    રા
    0.79
    ič
    0.78
     Off
    0.77
    명
    0.77
    iť
    0.75
    off
    0.73
    Off
    0.71
    ivní
    0.69
    ър
    0.68
    Act Density 0.023%

    No Known Activations