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

    Neuronpedia

    INDEX
    Explanations

    commas and sentence delimiters

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

    Follows punctuation (,).) or a quotation mark

    np_acts-logits-general · gemini-2.0-flash

    Q and A structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RenderAtEndOf
    -0.87
    ^(@)
    -0.70
     يتيمه
    -0.69
     Theſe
    -0.67
     (\<
    -0.65
    ]`
    -0.62
    OrBuilder
    -0.61
     myſelf
    -0.61
     ddelweddau
    -0.60
     Forumite
    -0.60
    POSITIVE LOGITS
     and
    0.84
     but
    0.63
     wireType
    0.60
    而
    0.54
     And
    0.54
     محفوظة
    0.47
    ந்து
    0.47
    And
    0.46
     even
    0.46
    and
    0.45
    Act Density 0.056%

    No Known Activations