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

    Neuronpedia

    INDEX
    Explanations

    references to significant events, announcements, or updates

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

    big or major preceding nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     costumbres
    -0.40
     poète
    -0.36
     saisons
    -0.35
     préféré
    -0.33
     murni
    -0.32
     seizoen
    -0.31
     élu
    -0.31
     percorso
    -0.31
     суток
    -0.31
    spesies
    -0.31
    POSITIVE LOGITS
     big
    0.88
    big
    0.81
     BIG
    0.80
    BIG
    0.79
    Big
    0.75
    important
    0.74
    hoeddwyd
    0.74
     Important
    0.74
     للاسماء
    0.73
    ビッグ
    0.73
    Act Density 0.021%

    No Known Activations