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

    Neuronpedia

    INDEX
    Explanations

    SQL VALUES clauses and Node.js packages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    h
    0.71
    ణి
    0.70
    s
    0.70
    ات
    0.69
    Jenis
    0.69
    ς
    0.69
    ानंतर
    0.68
    ным
    0.68
    없는
    0.68
    시
    0.67
    POSITIVE LOGITS
    ﺍ
    0.78
     perfumes
    0.77
     Shirts
    0.76
    monium
    0.75
     ตั้ง
    0.75
    ♪
    0.73
    isetas
    0.73
    🫧
    0.72
     Soh
    0.72
    ८
    0.71
    Act Density 0.002%

    No Known Activations