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

    Neuronpedia

    INDEX
    Explanations

    musical notes and programming constructs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    }),
    1.01
    운
    0.84
    </tr>
    0.82
    나
    0.80
    }},
    0.79
    ’
    0.77
    ‌
    0.76
    issive
    0.75
    },
    0.73
     corresponding
    0.73
    POSITIVE LOGITS
    re
    1.38
    㗎
    0.96
    rean
    0.95
    ัพท์
    0.92
     skú
    0.89
     siege
    0.88
    unteer
    0.86
    өк
    0.85
    ASMA
    0.85
     ابھی
    0.85
    Act Density 0.001%

    No Known Activations