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

    Neuronpedia

    INDEX
    Explanations

    alphabet

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    airro
    -0.07
    ILLISE
    -0.07
     수상
    -0.07
    難
    -0.07
    195
    -0.07
    _request
    -0.06
     ir
    -0.06
    985
    -0.06
     lines
    -0.06
     Dann
    -0.06
    POSITIVE LOGITS
     Alphabet
    0.12
     alphabet
    0.12
    phabet
    0.11
    alphabet
    0.09
     alph
    0.08
    0.08
     diet
    0.07
     doGet
    0.07
     alphabetical
    0.07
     alot
    0.07
    Act Density 0.003%

    No Known Activations