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

    Neuronpedia

    INDEX
    Explanations

    indicators of a formal or structured context, such as programming or technical documentation

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

    Code, categories, or technical jargon

    np_acts-logits-general · gemini-2.0-flash

    mathematical and code symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    CopyWith
    -0.78
    (!__
    -0.65
    EndContext
    -0.63
    出版年
    -0.58
    دانشنامهٔ
    -0.58
    хьтан
    -0.53
    MENAFN
    -0.52
     My
    -0.50
    #
    -0.48
    _,
    -0.48
    POSITIVE LOGITS
    itemize
    0.84
    mybatisplus
    0.66
     PMA
    0.66
     tori
    0.63
     Trait
    0.62
    ItemBackground
    0.61
    λέον
    0.61
     Cakes
    0.60
    UnusedPrivate
    0.60
     trait
    0.60
    Act Density 0.021%

    No Known Activations