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

    Neuronpedia

    INDEX
    Explanations

    words and phrases that indicate an idea or abstract concept

    oai_token-act-pair · gemini-2.0-flash

    words with specific prefixes or being in French

    np_token-act-pair-logits · gpt-4o-mini

    draw

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    #+#
    -0.97
    Abitanti
    -0.90
     الرياضيه
    -0.82
     betweenstory
    -0.74
    AntiForgeryToken
    -0.73
    IndentedString
    -0.67
     Italijanski
    -0.66
    raborty
    -0.66
    Vidite
    -0.65
    oa̍t
    -0.65
    POSITIVE LOGITS
     démocr
    0.55
     paard
    0.55
     graças
    0.55
     manqué
    0.54
     économiques
    0.53
     capables
    0.52
    ğer
    0.52
     épaules
    0.52
     juridiques
    0.52
     titolata
    0.51
    Act Density 8.303%

    No Known Activations