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

    Neuronpedia

    INDEX
    Explanations

    possessive pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    이었다
    -0.08
     */)
    -0.07
    .Serialization
    -0.07
     swingers
    -0.07
    าม
    -0.06
    -r
    -0.06
    แรง
    -0.06
    觉
    -0.06
     enum
    -0.06
    jwt
    -0.06
    POSITIVE LOGITS
    -strokes
    0.07
    phia
    0.06
     ubiqu
    0.06
     Schn
    0.06
     Carly
    0.06
    =sub
    0.06
     athletes
    0.06
    .strip
    0.06
     genellikle
    0.06
     ais
    0.06
    Act Density 0.019%

    No Known Activations