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

    Neuronpedia

    INDEX
    Explanations

    a mix of words related to web design, Russian language code snippets and the natural world

    oai_token-act-pair · gemini-2.0-flash

    Foreign language

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     armée
    -0.63
     hiér
    -0.62
     définiti
    -0.57
     démission
    -0.56
     assuré
    -0.53
     renon
    -0.52
     rédaction
    -0.52
     disparu
    -0.52
    zło
    -0.52
     négo
    -0.50
    POSITIVE LOGITS
    IndentedString
    0.63
    <bos>
    0.62
    okovic
    0.60
     betweenstory
    0.57
    VIAF
    0.57
     propOrder
    0.57
    Tembelea
    0.54
     виправивши
    0.54
     autorytatywna
    0.53
    expandindo
    0.52
    Act Density 2.297%

    No Known Activations