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

    Neuronpedia

    INDEX
    Explanations

    technical terms and structured data related to account management and configuration

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

    $lang strings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     мәкал
    -0.97
     snippetHide
    -0.94
    RenderAtEndOf
    -0.83
     CreateTagHelper
    -0.79
     OMITBAD
    -0.77
    expandindo
    -0.74
     يتيمه
    -0.74
    MigrationBuilder
    -0.74
     ویکی‌پدی
    -0.73
     незавершена
    -0.73
    POSITIVE LOGITS
    1
    0.40
     written
    0.40
     language
    0.39
    2
    0.39
    7
    0.35
     Language
    0.35
     text
    0.35
    language
    0.34
    9
    0.34
     Jeremy
    0.32
    Act Density 0.115%

    No Known Activations