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

    Neuronpedia

    INDEX
    Explanations

    App namespaces

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    人形
    0.43
    ሂ
    0.43
    丈
    0.42
    ﺄ
    0.42
     strany
    0.42
     آب
    0.41
     boric
    0.40
    がありますが
    0.40
    皂
    0.39
     انتخاب
    0.39
    POSITIVE LOGITS
    \
    0.64
     '\
    0.56
    '\
    0.52
    \\
    0.50
     "\
    0.48
     namespace
    0.46
    "\
    0.43
     '\\
    0.43
    \\\
    0.42
    uki
    0.42
    Act Density 0.000%

    No Known Activations