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

    Neuronpedia

    INDEX
    Explanations

    common words

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     「
    0.42
    =<
    0.39
     “[
    0.38
     ＜
    0.37
     analogous
    0.37
     등
    0.37
     Taq
    0.36
     Density
    0.36
     ■
    0.36
     IPCC
    0.35
    POSITIVE LOGITS
    of
    0.54
    into
    0.52
    been
    0.49
    than
    0.44
     into
    0.42
    讶
    0.42
    their
    0.41
    that
    0.40
    to
    0.39
    for
    0.39
    Act Density 0.012%

    No Known Activations