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

    Neuronpedia

    INDEX
    Explanations

    content types and structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    。
    0.35
    Test
    0.34
    ：
    0.34
    (,
    0.34
    \
    0.32
    【
    0.31
    Closing
    0.31
    :
    0.31
    (
    0.31
    ::
    0.30
    POSITIVE LOGITS
     thats
    0.52
     similaires
    0.45
     ranging
    0.44
     galore
    0.43
     jotka
    0.43
     που
    0.42
     that
    0.41
     like
    0.41
     столь
    0.41
     kutoka
    0.41
    Act Density 0.354%

    No Known Activations