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

    Neuronpedia

    INDEX
    Explanations

    expressions of concern or frustration regarding government policies and societal issues

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

    Punctuation followed by specific prepositions

    np_acts-logits-general · gemini-2.0-flash

    expressive punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    UnsafeEnabled
    -0.63
    ulmuş
    -0.60
    IsMutable
    -0.58
     Мексичка
    -0.58
     presumably
    -0.57
    ❷
    -0.57
    ########.
    -0.56
     overras
    -0.55
    帖最后由
    -0.55
     pháp
    -0.55
    POSITIVE LOGITS
     sorry
    0.57
     Sorry
    0.55
     hope
    0.55
    drawSprites
    0.53
    Wake
    0.53
     Hope
    0.53
     wünsche
    0.53
    加油
    0.52
     espero
    0.52
     Cheers
    0.52
    Act Density 0.347%

    No Known Activations