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

    Neuronpedia

    INDEX
    Explanations

    dates and years

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ating
    0.45
     mẽ
    0.42
    垛
    0.41
     supre
    0.41
    すすめ
    0.41
     belladone
    0.41
    جمالي
    0.41
    ხვევ
    0.40
    \".
    0.39
     spez
    0.39
    POSITIVE LOGITS
    न
    0.48
    ﻟ
    0.47
    coords
    0.43
    n
    0.43
    anagram
    0.42
    คโน
    0.42
     irradiance
    0.42
    𝕂
    0.42
    ర్
    0.41
    ్
    0.41
    Act Density 0.010%

    No Known Activations