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

    Neuronpedia

    INDEX
    Explanations

    numbers in different languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Rajas
    0.84
     rebel
    0.72
     Rebel
    0.66
     prospect
    0.65
     Someone
    0.65
     myst
    0.65
     낮은
    0.64
     inclination
    0.64
     τ
    0.63
     Prospect
    0.63
    POSITIVE LOGITS
    ೬
    0.88
     twos
    0.86
     дву
    0.86
    ẵn
    0.86
    dois
    0.85
     четыре
    0.85
     kahe
    0.85
     २४
    0.84
    deux
    0.83
    quatre
    0.82
    Act Density 0.309%

    No Known Activations