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

    Neuronpedia

    INDEX
    Explanations

    references related to lists or indexes in various contexts

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

    References and category

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.98
    AnimationsModule
    -0.95
     defaultstate
    -0.80
    tvguidetime
    -0.79
    httphttps
    -0.79
    Aktualisiert
    -0.76
     <>",
    -0.74
     kasarigan
    -0.74
    Билгалдахарш
    -0.73
     queſta
    -0.72
    POSITIVE LOGITS
    <eos>
    0.43
    .
    0.29
     Wikiseite
    0.28
     Exteriores
    0.27
    ↵↵
    0.26
     nahilalakip
    0.26
     --
    0.26
     kaikki
    0.25
     —
    0.23
    ---
    0.21
    Act Density 0.003%

    No Known Activations