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

    Neuronpedia

    INDEX
    Explanations

    terms related to localized actions or attributes within various contexts

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

    localized effects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     StatefulWidget
    -0.61
    IntoConstraints
    -0.51
     ſtand
    -0.50
     ſta
    -0.48
    labus
    -0.48
     Reſ
    -0.48
    adaptiveStyles
    -0.47
     Dividend
    -0.47
    enfone
    -0.47
     trains
    -0.47
    POSITIVE LOGITS
    local
    0.57
    Local
    0.51
     localized
    0.50
     lokalen
    0.50
    Localized
    0.49
     lokale
    0.49
     Locally
    0.49
     Local
    0.49
     localised
    0.48
    Locally
    0.48
    Act Density 0.178%

    No Known Activations