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

    Neuronpedia

    INDEX
    Explanations

    punctuations and structural elements in text

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

    ending in "-ing" followed by a comma

    np_acts-logits-general · gemini-2.0-flash

    end of sentence/clause

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     заключается
    -0.60
    IUrlHelper
    -0.56
    harusnya
    -0.54
    还有一个
    -0.53
     родился
    -0.52
    还有一
    -0.51
    árna
    -0.50
    ulto
    -0.49
    śred
    -0.49
    rivial
    -0.49
    POSITIVE LOGITS
     realizing
    1.21
     having
    1.18
     knowing
    1.13
     taking
    1.10
     recognizing
    1.10
     realising
    1.09
     using
    1.09
     fearing
    1.08
     believing
    1.08
     wanting
    1.04
    Act Density 0.334%

    No Known Activations