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

    Neuronpedia

    INDEX
    Explanations

    cap word start

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    桫
    -0.98
    ERIES
    -0.95
    '
    -0.92
     regards
    -0.91
    ameter
    -0.90
    '%(
    -0.90
    を読
    -0.88
     catalán
    -0.88
    ίες
    -0.82
    妧
    -0.82
    POSITIVE LOGITS
     Cap
    1.31
     cap
    1.10
    Cap
    1.09
     CAP
    1.08
    🧢
    1.04
    CAP
    1.00
    水墨
    0.93
     şehir
    0.92
    cap
    0.91
     Coral
    0.91
    Act Density 0.056%

    No Known Activations