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

    Neuronpedia

    INDEX
    Explanations

    does not constitute medical advice

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    वादियों
    0.50
    ]$;
    0.47
    مجھے
    0.46
    ]+/
    0.46
    রিষ্ঠ
    0.46
    帶著
    0.46
    怎样的
    0.45
    َالَ
    0.44
    ದಯ
    0.44
    âne
    0.44
    POSITIVE LOGITS
     and
    0.46
    และ
    0.44
     raisins
    0.40
     trims
    0.39
     Polskiej
    0.39
    앞
    0.39
     Over
    0.38
     drizzle
    0.38
    ಕ್ಕಿಂತ
    0.38
     và
    0.38
    Act Density 0.001%

    No Known Activations