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

    Neuronpedia

    INDEX
    Explanations

    references to official capacity or status

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

    official followed by descriptor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Desenvolvimento
    -0.52
     Spine
    -0.52
    nextProps
    -0.49
     pyram
    -0.48
     Nebraska
    -0.45
     Kanye
    -0.45
    lerinde
    -0.45
     Andromeda
    -0.45
    Spine
    -0.45
    Égypte
    -0.44
    POSITIVE LOGITS
     official
    1.84
     Official
    1.82
    Official
    1.79
    official
    1.73
     OFFICIAL
    1.62
    OFFICIAL
    1.55
     officially
    1.31
     oficial
    1.31
     unofficial
    1.23
     officiel
    1.20
    Act Density 0.007%

    No Known Activations