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

    Neuronpedia

    INDEX
    Explanations

    folk tales, lore, songs, art

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     garn
    0.37
     সফ
    0.37
    কাণ্ড
    0.37
     baud
    0.36
    علم
    0.36
     Neon
    0.36
     intram
    0.36
     aguas
    0.35
     COND
    0.35
    Coef
    0.35
    POSITIVE LOGITS
    lores
    0.90
    lor
    0.85
    lore
    0.80
    Lore
    0.76
     lore
    0.74
     Lore
    0.71
    klore
    0.70
     folk
    0.66
     fol
    0.64
     folklore
    0.64
    Act Density 0.004%

    No Known Activations