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

    Neuronpedia

    INDEX
    Explanations

    contradictory statements or contextually important qualifiers

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

    whether or not

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    pula
    -0.40
    Literatuur
    -0.36
     handleClick
    -0.36
    ElementAt
    -0.35
     lom
    -0.35
     Flight
    -0.34
    дцать
    -0.34
    FormTagHelper
    -0.34
    propTypes
    -0.33
    kauft
    -0.33
    POSITIVE LOGITS
    IsContent
    0.64
    principalColumn
    0.53
     ProtoMessage
    0.46
     zijne
    0.45
    帖最后由
    0.45
    adaptiveStyles
    0.43
     Lainnya
    0.42
     chaqueta
    0.42
    ValueStyle
    0.42
     rehabilitación
    0.41
    Act Density 0.176%

    No Known Activations