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

    Neuronpedia

    INDEX
    Explanations

    "in" across languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    啻
    0.42
    िशियल
    0.41
     anisot
    0.40
    exterior
    0.40
    Motivation
    0.39
    蘋
    0.38
    𒋗
    0.38
     यूपीएससी
    0.38
    chromo
    0.38
    妛
    0.38
    POSITIVE LOGITS
     イン
    1.70
     ин
    1.69
    イン
    1.66
     ін
    1.66
     Ин
    1.48
    อิน
    1.45
     인
    1.39
    Ин
    1.37
     ინ
    1.33
     Ін
    1.27
    Act Density 0.699%

    No Known Activations