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

    Neuronpedia

    INDEX
    Explanations

    ร followed by syllables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ри
    0.42
    డ్
    0.40
    డ్‌
    0.39
    ֛
    0.39
     Costa
    0.39
    вай
    0.38
     Estr
    0.38
    ارين
    0.38
    tar
    0.37
     Evo
    0.37
    POSITIVE LOGITS
    upol
    0.45
     morphologies
    0.43
     styles
    0.43
    क्षण
    0.41
     greens
    0.41
     learns
    0.41
     tastes
    0.41
    until
    0.41
    ungy
    0.41
     şidd
    0.41
    Act Density 0.001%

    No Known Activations