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

    Neuronpedia

    INDEX
    Explanations

    grammatical endings across languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     I
    0.54
    ieten
    0.43
    iamo
    0.43
    卞
    0.41
    อย่าง
    0.41
    ก็
    0.38
    ooker
    0.38
    ijen
    0.38
    unu
    0.37
    iveness
    0.37
    POSITIVE LOGITS
    ar
    0.82
    et
    0.80
    an
    0.76
    us
    0.66
    ur
    0.64
    на
    0.64
    ad
    0.63
    p
    0.63
    ab
    0.61
    and
    0.61
    Act Density 0.097%

    No Known Activations