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

    Neuronpedia

    INDEX
    Explanations

    punctuation and function syntax in code

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

    Code or configuration snippets with brackets/braces

    np_acts-logits-general · gemini-2.0-flash

    delimited structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    onton
    -0.31
     דרך
    -0.31
    ansen
    -0.30
     Wim
    -0.30
    moveTo
    -0.29
    蚓
    -0.29
    Thumbnail
    -0.29
    ճ
    -0.29
    through
    -0.29
    算是
    -0.28
    POSITIVE LOGITS
    RuleContext
    0.84
    +#+#
    0.74
     الرياضيه
    0.70
    AddTagHelper
    0.67
    ftagPool
    0.66
    stateProvider
    0.64
    Portail
    0.63
    BagConstraints
    0.62
    NameInMap
    0.62
    Hentet
    0.60
    Act Density 0.162%

    No Known Activations