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

    Neuronpedia

    INDEX
    Explanations

    references to documents and links in a technical or academic context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    File extensions and currency symbols

    np_acts-logits-general · gemini-2.0-flash

    technical documentation or academic papers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Arrondissement
    -0.51
     trajets
    -0.48
     _)
    -0.47
     >=",
    -0.46
     uska
    -0.46
     Cf
    -0.46
    IVEREF
    -0.46
    posites
    -0.45
    يميديا
    -0.45
    ScopeManager
    -0.45
    POSITIVE LOGITS
     به
    0.88
     در
    0.86
     از
    0.84
    ،
    0.81
     با
    0.79
     برای
    0.77
     که
    0.73
    به
    0.69
    در
    0.68
     بط
    0.67
    Act Density 0.003%

    No Known Activations