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

    Neuronpedia

    INDEX
    Explanations

    excerpts from interview transcripts

    oai_token-act-pair · gemini-2.0-flash

    dialogue excerpts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     her
    -0.58
    XmlAccessType
    -0.48
     مؤرشف
    -0.47
    Hentet
    -0.46
    endregion
    -0.46
    parsedMessage
    -0.45
     otomatig
    -0.43
    لمه
    -0.43
    contentLoaded
    -0.42
    MemoryWarning
    -0.42
    POSITIVE LOGITS
     Efq
    0.65
     quadrature
    0.65
     }}"></
    0.65
    ArgsConstructor
    0.64
     itſelf
    0.63
     Shaksp
    0.62
     ویکی‌پدیای
    0.62
     Shakspeare
    0.61
     Phry
    0.60
     nephe
    0.60
    Act Density 0.937%

    No Known Activations