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

    Neuronpedia

    INDEX
    Explanations

    citations, URLs, and legal or formal text markers

    oai_token-act-pair · gemini-2.0-flash

    legal/technical documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <bos>
    -0.88
    ↵↵
    -0.60
     Leurs
    -0.58
    uxxxx
    -0.54
     Garibaldi
    -0.53
    </table>
    -0.52
    <eos>
    -0.51
     AssemblyCulture
    -0.50
     Stardust
    -0.49
    ')],
    -0.49
    POSITIVE LOGITS
     BrowserModule
    0.63
    NUMX
    0.60
    itania
    0.57
    styleType
    0.57
    ThroughAttribute
    0.56
     تانيه
    0.54
    Kariera
    0.54
    /-/
    0.52
    arrings
    0.52
    Publishing
    0.50
    Act Density 3.529%

    No Known Activations