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

    Neuronpedia

    INDEX
    Explanations

    sentences or phrases that indicate the end of a section or document

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

    Follows a period

    np_acts-logits-general · gemini-2.0-flash

    legal names and specific terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     שוליים
    -0.72
     كومونز
    -0.71
    Revenir
    -0.70
    -0.67
    __':
    -0.67
     հղումներ
    -0.67
     ivelany
    -0.62
    AndEndTag
    -0.62
    PreferredItem
    -0.61
    findpost
    -0.61
    POSITIVE LOGITS
     In
    0.48
    guro
    0.48
    M
    0.46
     It
    0.45
    Areas
    0.45
    addEventListener
    0.44
    ById
    0.44
     Others
    0.44
     mét
    0.43
    In
    0.43
    Act Density 0.181%

    No Known Activations