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

    Neuronpedia

    INDEX
    Explanations

    Alphabets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Schmerz
    -0.07
     SUVs
    -0.07
     palpable
    -0.07
    precision
    -0.07
     mud
    -0.07
    iculous
    -0.07
    embed
    -0.07
     threads
    -0.07
    Mult
    -0.07
    iscus
    -0.06
    POSITIVE LOGITS
     alphabet
    0.14
     alfabet
    0.14
    Alphabet
    0.13
     Alphabet
    0.12
    alphabet
    0.12
    ABCDEFGHIJKLMNOPQRSTUVWXYZ
    0.11
    abcdefghijklmnopqrstuvwxyz
    0.11
     alphabetical
    0.11
    phabet
    0.11
     alph
    0.11
    Act Density 0.011%

    No Known Activations