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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and their associated contexts

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

    Commas followed by pronouns or conjunctions

    np_acts-logits-general · gemini-2.0-flash

    conjunctions and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     gynhyrchwyd
    -0.82
    Espèce
    -0.79
     Chwiliwch
    -0.79
     referenties
    -0.77
     lenker
    -0.75
     AssemblyCulture
    -0.75
    !".
    -0.72
    ########.
    -0.71
    !”.
    -0.70
    ).-
    -0.68
    POSITIVE LOGITS
     and
    0.72
     (
    0.55
     or
    0.54
    以及
    0.53
    <sup>
    0.51
     it
    0.49
     we
    0.48
     ranging
    0.47
    ,
    0.46
     والتي
    0.45
    Act Density 0.487%

    No Known Activations