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

    Neuronpedia

    INDEX
    Explanations

    URI

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Logger
    -0.07
     encode
    -0.06
    Nos
    -0.06
     dames
    -0.06
    劃
    -0.06
    .book
    -0.06
    Wildcard
    -0.06
    44
    -0.06
    reg
    -0.06
     programmer
    -0.06
    POSITIVE LOGITS
     json
    0.07
     petty
    0.07
     varchar
    0.07
     subtle
    0.06
     pard
    0.06
     ]]
    0.06
    toFloat
    0.06
    사진
    0.06
     splendid
    0.06
     hindi
    0.06
    Act Density 0.009%

    No Known Activations