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

    Neuronpedia

    INDEX
    Explanations

    if you needed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     வெற்ற
    0.45
    Боль
    0.44
    ביע
    0.44
     sought
    0.43
     wage
    0.41
     chauffeur
    0.40
     signified
    0.40
    くれる
    0.40
     successful
    0.39
     chairperson
    0.39
    POSITIVE LOGITS
     ಬಳಸ
    0.45
    を使用
    0.45
    use
    0.43
     whiche
    0.43
     andere
    0.42
    }=-\
    0.41
    ใช
    0.41
    lu
    0.41
     Using
    0.41
     사용
    0.41
    Act Density 0.032%

    No Known Activations