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

    Neuronpedia

    INDEX
    Explanations

    digits and change

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    र्ता
    0.79
    दत
    0.73
    ନା
    0.72
     Fastest
    0.70
    тернет
    0.69
    iegler
    0.68
     earliest
    0.67
     Efficient
    0.66
    Erst
    0.66
     empowerment
    0.65
    POSITIVE LOGITS
    ऱ्यावर
    0.83
    0.78
    مع
    0.78
    mt
    0.75
     časti
    0.75
     ನಡೆ
    0.74
    لو
    0.74
    pub
    0.74
     uključ
    0.73
    लिख
    0.73
    Act Density 0.000%

    No Known Activations