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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and their context within sentences

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

    Sentences starting with enumeration adverbs

    np_acts-logits-general · gemini-2.0-flash

    starts of lists or explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     the
    -1.09
     a
    -0.99
     in
    -0.97
     this
    -0.93
     as
    -0.91
     even
    -0.91
     all
    -0.91
     that
    -0.88
     no
    -0.88
     to
    -0.88
    POSITIVE LOGITS
     NSCoder
    0.90
    دانشنامهٔ
    0.81
    ########.
    0.81
    enderror
    0.78
    :✨
    0.78
     ་་
    0.76
     kasarigan
    0.76
     متعلقه
    0.75
    #+#
    0.75
    HostException
    0.74
    Act Density 0.817%

    No Known Activations