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

    Neuronpedia

    INDEX
    Explanations

    adjectives in Russian -н- and Latin -n

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    တွေကို
    0.64
    ষণ
    0.63
    olaire
    0.63
    сси
    0.62
    whal
    0.61
     Inu
    0.61
    ాత్రి
    0.61
     થો
    0.60
     balo
    0.59
     செல்சியஸ்
    0.59
    POSITIVE LOGITS
    ный
    1.34
    ные
    1.33
    ное
    1.33
    ным
    1.18
    ному
    1.15
    ного
    1.11
    ная
    1.10
    ny
    1.09
    ными
    1.04
    ную
    1.00
    Act Density 0.051%

    No Known Activations