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

    Neuronpedia

    INDEX
    Explanations

    get started or get it

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dotyczą
    1.52
    是我
    1.45
    é
    1.39
    有助于
    1.34
    你
    1.34
    に示す
    1.33
     związ
    1.32
    ları
    1.30
    異なる
    1.29
    ्स
    1.28
    POSITIVE LOGITS
     rid
    1.87
    rän
    1.69
    ل
    1.54
     phép
    1.49
    у
    1.49
    id
    1.30
     antérieure
    1.30
    al
    1.27
    ยิน
    1.27
    iatric
    1.25
    Act Density 0.118%

    No Known Activations