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

    Neuronpedia

    INDEX
    Explanations

    illuminated by light

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    t
    1.21
    s
    1.09
    z
    1.07
    es
    0.99
    r
    0.94
    ne
    0.93
    y
    0.91
    m
    0.88
    ing
    0.84
    i
    0.84
    POSITIVE LOGITS
     illuminate
    1.09
    Lighting
    1.03
    0
    0.99
     Lighting
    0.97
     illuminates
    0.96
     Lights
    0.95
    Lights
    0.95
     Illuminate
    0.94
     照明
    0.93
     iluminación
    0.91
    Act Density 0.022%

    No Known Activations