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

    Neuronpedia

    INDEX
    Explanations

    languages, explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ️⃣
    0.92
    ⃣
    0.90
     ​​
    0.82
    ฀
    0.82
    ️
    0.80
    ︎
    0.79
    ২
    0.77
    ‐
    0.76
    ⾏
    0.75
     axon
    0.74
    POSITIVE LOGITS
    ங்களால்
    0.74
    hydrate
    0.73
    hauses
    0.72
    Finalmente
    0.71
     такой
    0.70
    icul
    0.69
    зы
    0.69
    itu
    0.68
    বৃদ্ধি
    0.67
    unan
    0.67
    Act Density 0.873%

    No Known Activations