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

    Neuronpedia

    INDEX
    Explanations

    AI concepts and programming

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ’
    0.55
     namani
    0.41
     plaie
    0.39
    𝕟
    0.39
    sru
    0.38
     gacche
    0.38
    龰
    0.38
    '।
    0.36
    sodium
    0.36
    ，「
    0.36
    POSITIVE LOGITS
     in
    0.61
    Y
    0.50
    지
    0.50
     and
    0.47
    도
    0.46
    ین
    0.44
    in
    0.44
    पणे
    0.41
    ↵
    0.41
     the
    0.41
    Act Density 3.051%

    No Known Activations