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

    Neuronpedia

    INDEX
    Explanations

    non-English language or eligibility

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ไง
    0.44
    onimo
    0.44
     duty
    0.39
    ómo
    0.38
     موز
    0.37
    ऊं
    0.37
    adım
    0.37
    )$-
    0.37
    ключение
    0.36
    +|
    0.36
    POSITIVE LOGITS
    距離
    0.42
     geot
    0.42
     দৃ
    0.41
     elettronica
    0.40
    Ფ
    0.39
    歐洲
    0.39
     incertid
    0.38
    𒋼
    0.38
     stessa
    0.38
     geometria
    0.37
    Act Density 0.000%

    No Known Activations