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

    Neuronpedia

    INDEX
    Explanations

    using list

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     zároveň
    0.37
    题材
    0.35
     बहुत
    0.34
    ど
    0.33
    ทาง
    0.32
    áb
    0.32
    ญาต
    0.32
    नंतर
    0.31
     تباہ
    0.31
     terenie
    0.31
    POSITIVE LOGITS
     दिखी
    0.40
    BrI
    0.34
     آیا
    0.34
    恂
    0.34
    phine
    0.33
     Vidy
    0.33
    FlatStyle
    0.33
    0.33
    索引
    0.32
     శ్రీ
    0.32
    Act Density 0.218%

    No Known Activations