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

    Neuronpedia

    INDEX
    Explanations

    technical terms or acronym starts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ನಾವು
    0.42
     essa
    0.38
     înt
    0.38
     aastal
    0.37
    Ꮈ
    0.37
    簹
    0.37
    えない
    0.37
    ssä
    0.37
    ក្នុង
    0.36
    iamo
    0.36
    POSITIVE LOGITS
    ’
    0.44
    ardır
    0.38
    ”
    0.38
    σιμοποι
    0.37
    parking
    0.36
    url
    0.36
     অথবা
    0.36
    -
    0.36
    tab
    0.36
    ocation
    0.34
    Act Density 0.065%

    No Known Activations