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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the provision of information or resources

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

    preceding benefits or advantages

    np_acts-logits-general · gemini-2.0-flash

    providing value or benefit

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     defaultstate
    -0.59
     houſe
    -0.57
     queſta
    -0.53
    basicConfig
    -0.53
     depositphotos
    -0.52
    ArgsConstructor
    -0.52
     nakalista
    -0.48
    queryInterface
    -0.47
    最快更新
    -0.47
    AutoresizingMask
    -0.45
    POSITIVE LOGITS
     insight
    0.62
     insights
    0.54
     reassurance
    0.54
     opportunities
    0.52
     a
    0.52
     relief
    0.52
     respite
    0.50
     impetus
    0.49
    gives
    0.49
     support
    0.49
    Act Density 0.217%

    No Known Activations