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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    +#+#
    -0.88
    tonode
    -0.86
    Vidite
    -0.83
    :✨
    -0.81
    يكب
    -0.80
    脚注の使い方
    -0.80
    thâu
    -0.77
    GTCX
    -0.77
    MessageTagHelper
    -0.76
     continúas
    -0.72
    POSITIVE LOGITS
     the
    0.64
     épaules
    0.48
     all
    0.44
     Wort
    0.43
     even
    0.42
     ever
    0.41
     more
    0.40
     a
    0.40
     Zahn
    0.39
    kriv
    0.38
    Act Density 0.001%

    No Known Activations