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

    Neuronpedia

    INDEX
    Explanations

    references to legal concepts and implications

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

    followed by punctuation

    np_acts-logits-general · gemini-2.0-flash

    nor, not, or

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     defaultstate
    -0.67
    而不是
    -0.65
    MessageTagHelper
    -0.63
    nościo
    -0.62
     riuscito
    -0.62
    而非
    -0.61
    ISupport
    -0.59
     ModelExpression
    -0.59
    addComponent
    -0.56
     nejen
    -0.56
    POSITIVE LOGITS
     nor
    2.67
    nor
    2.01
     Nor
    1.80
     anymore
    1.78
    Nor
    1.75
     melainkan
    1.59
     sondern
    1.59
    而是
    1.42
     NOR
    1.35
     אלא
    1.32
    Act Density 0.947%

    No Known Activations