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

    Neuronpedia

    INDEX
    Explanations

    numerical values, specifically representing significant data points or metrics

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

    47 followed by numbers or symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Abb
    -0.44
     Epi
    -0.43
     Lek
    -0.40
     immers
    -0.39
     Bord
    -0.39
     epi
    -0.38
     bm
    -0.38
    word
    -0.38
     EZ
    -0.38
     Zw
    -0.37
    POSITIVE LOGITS
    ſelves
    0.70
     wikipagina
    0.62
    ftagPool
    0.60
     saveiro
    0.60
     desmotivaciones
    0.60
    parsedMessage
    0.60
     dourada
    0.60
    ########.
    0.57
    GenerationType
    0.56
    PreferredItem
    0.56
    Act Density 0.038%

    No Known Activations