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

    Neuronpedia

    INDEX
    Explanations

    visual glitches

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ῴ
    0.38
    fordul
    0.37
     Texture
    0.36
    pixels
    0.35
    tiered
    0.35
     திருமணம்
    0.35
     Pixel
    0.34
    tBleStatus
    0.34
     fulfil
    0.33
     Yr
    0.33
    POSITIVE LOGITS
     now
    0.50
     maintenant
    0.48
     sekarang
    0.44
     hopefully
    0.43
     agora
    0.43
     leçon
    0.43
     ahora
    0.41
    now
    0.41
     adesso
    0.41
    lesson
    0.40
    Act Density 0.000%

    No Known Activations