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

    Neuronpedia

    INDEX
    Explanations

    quality of light

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ピオン
    0.39
     수행
    0.39
     textes
    0.38
     Phrase
    0.38
    voicing
    0.38
    reements
    0.38
    Phrase
    0.38
    criminal
    0.37
     escuch
    0.36
     listens
    0.36
    POSITIVE LOGITS
     lighting
    2.19
     illumination
    2.03
     sunlight
    1.99
     Lighting
    1.93
    Lighting
    1.93
     iluminación
    1.90
    照明
    1.88
     lights
    1.80
     illuminating
    1.73
     cahaya
    1.73
    Act Density 0.095%

    No Known Activations