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

    Neuronpedia

    INDEX
    Explanations

    light properties and effects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    л
    0.80
    ের
    0.66
    ς
    0.62
    ओं
    0.56
    들이
    0.52
    af
    0.49
    á
    0.49
    ’.
    0.48
    ?’
    0.48
     मदद
    0.48
    POSITIVE LOGITS
    n
    0.98
    н
    0.68
     it
    0.65
     light
    0.59
     Light
    0.56
    a
    0.56
    нский
    0.55
     aprob
    0.54
    nál
    0.53
    t
    0.53
    Act Density 0.072%

    No Known Activations