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

    Neuronpedia

    INDEX
    Explanations

    light and brightness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     comma
    0.70
     compressibility
    0.68
     ঢে
    0.68
     अनी
    0.67
    ftp
    0.67
    Churn
    0.67
    िश्वत
    0.66
     কুর
    0.65
    ործ
    0.63
    য়দ
    0.63
    POSITIVE LOGITS
     lighting
    3.36
     light
    3.23
     illumination
    3.22
     lights
    3.19
     lumière
    3.00
    Lighting
    2.98
     Lighting
    2.97
     sunlight
    2.93
     cahaya
    2.83
     illuminate
    2.79
    Act Density 0.867%

    No Known Activations