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

    Neuronpedia

    INDEX
    Explanations

    sections with technical or programming-related content

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

    Code, acknowledgements, or unusual punctuation

    np_acts-logits-general · gemini-2.0-flash

    acknowledgements with separators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    vant
    -0.66
    mybatisplus
    -0.64
    ull
    -0.57
     Wheeler
    -0.57
    Collegamenti
    -0.57
    FetchType
    -0.56
     Ayres
    -0.55
    レーキ
    -0.54
    Дере
    -0.53
    PathVariable
    -0.53
    POSITIVE LOGITS
     ModelExpression
    0.69
    TagMode
    0.57
     Huguen
    0.55
    utnik
    0.54
    )».
    0.53
    पया
    0.53
     Grecian
    0.53
     Siamese
    0.52
     meli
    0.52
     viad
    0.51
    Act Density 0.002%

    No Known Activations