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

    Neuronpedia

    INDEX
    Explanations

    in some cases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    imy
    0.74
    ig
    0.70
    l
    0.69
    ll
    0.67
    il
    0.67
     Ubuy
    0.65
    oy
    0.64
    iye
    0.64
    llen
    0.63
    ^
    0.63
    POSITIVE LOGITS
     почти
    0.86
     майже
    0.76
     είχε
    0.72
     meski
    0.71
     redux
    0.71
     கிட்டத்தட்ட
    0.70
    雖
    0.67
     quase
    0.67
    こういう
    0.67
     गरजेचे
    0.66
    Act Density 0.003%

    No Known Activations