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

    Neuronpedia

    INDEX
    Explanations

    topics related to social research and scholarly citations

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

    Follows "by" or a period

    np_acts-logits-general · gemini-2.0-flash

    academic authorship or research citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     azioni
    -0.59
     geométrico
    -0.56
    Spoljašnje
    -0.54
    eynman
    -0.54
     Shakspeare
    -0.54
     optique
    -0.52
     comerciales
    -0.52
     preghi
    -0.52
     milliard
    -0.52
    Kanpo
    -0.51
    POSITIVE LOGITS
     scholars
    0.87
     scholarly
    0.75
     researched
    0.72
     scholar
    0.71
    elemField
    0.69
     scholarship
    0.68
     research
    0.67
     studies
    0.67
     JSTOR
    0.66
    Scholars
    0.64
    Act Density 0.460%

    No Known Activations