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

    Neuronpedia

    INDEX
    Explanations

    letters to numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Haus
    -0.09
    高清视频
    -0.09
    债
    -0.08
     buenos
    -0.08
    奖金
    -0.08
     rocking
    -0.08
    منٹ
    -0.08
     ciment
    -0.08
    ечь
    -0.08
     стак
    -0.08
    POSITIVE LOGITS
     alphabetical
    0.14
     alph
    0.13
     alphabet
    0.11
     Alphabet
    0.11
    Alphabet
    0.11
     conson
    0.10
     अक्ष
    0.10
     chr
    0.10
     letters
    0.10
    abcdefghijklmnopqrstuvwxyz
    0.10
    Act Density 0.009%

    No Known Activations