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

    Neuronpedia

    INDEX
    Explanations

    ni án

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     የሚያ
    0.45
     Yn
    0.44
    <0x96>
    0.43
     yeast
    0.42
     Yeti
    0.42
     Yal
    0.41
    giveness
    0.41
    미
    0.40
    𝒂
    0.40
     य
    0.40
    POSITIVE LOGITS
     vu
    0.72
    Vu
    0.69
     Vu
    0.69
    vu
    0.63
     wu
    0.60
     VU
    0.59
     ву
    0.55
    ву
    0.53
     vue
    0.52
    吴
    0.51
    Act Density 0.001%

    No Known Activations