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

    Neuronpedia

    INDEX
    Explanations

    code formatting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Appear
    0.84
    ക്കം
    0.79
     Appear
    0.78
     Tetapi
    0.73
     Vill
    0.71
     appearance
    0.70
     Steck
    0.66
     Dự
    0.65
    しません
    0.64
     Investor
    0.63
    POSITIVE LOGITS
     estamos
    0.95
     components
    0.95
     specifics
    0.90
    要素
    0.89
     ಅಂಶ
    0.89
     суть
    0.85
    首先
    0.84
     тут
    0.83
     elements
    0.83
     luctus
    0.82
    Act Density 0.407%

    No Known Activations