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

    Neuronpedia

    INDEX
    Explanations

    common English tokens/punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .hour
    -0.07
     Hopefully
    -0.07
    azing
    -0.06
     tremend
    -0.06
     Malays
    -0.06
     eru
    -0.06
     dap
    -0.06
     basically
    -0.06
     meille
    -0.06
     camouflage
    -0.06
    POSITIVE LOGITS
    fts
    0.06
     TN
    0.06
    Padding
    0.06
     Skyl
    0.06
    ?>"↵
    0.06
     Cards
    0.06
    altura
    0.06
    Steve
    0.06
    δο
    0.06
     Note
    0.06
    Act Density 0.000%

    No Known Activations