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

    Neuronpedia

    INDEX
    Explanations

    patterns and structures within numerical or symbolic data

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

    Follows a period

    np_acts-logits-general · gemini-2.0-flash

    English Mathematics Science

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Efq
    -1.10
     myſelf
    -1.02
     itſelf
    -0.92
     uſed
    -0.91
     himſelf
    -0.91
     Waterman
    -0.90
     ―――――
    -0.90
     HasFactory
    -0.89
     themſelves
    -0.88
     roux
    -0.88
    POSITIVE LOGITS
     Elli
    0.69
    原始内容存档于
    0.67
     Dae
    0.65
    idigung
    0.61
    页面存档备份
    0.61
    :✨
    0.58
     .
    0.58
     Ernie
    0.58
     Morse
    0.56
    かっ
    0.56
    Act Density 0.156%

    No Known Activations