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

    Neuronpedia

    INDEX
    Explanations

    light and lighting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ulation
    0.70
    Registro
    0.70
    tion
    0.69
    ure
    0.68
    simeq
    0.67
     entice
    0.67
    ឫ
    0.66
    Integr
    0.65
    sides
    0.64
    Typography
    0.63
    POSITIVE LOGITS
     bulbs
    0.95
     bulb
    0.92
    bulb
    0.85
     beacons
    0.80
     airy
    0.78
     shining
    0.75
     sunlight
    0.74
    س
    0.74
     illuminate
    0.73
     Admittedly
    0.72
    Act Density 0.221%

    No Known Activations