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

    Neuronpedia

    INDEX
    Explanations

    references and bibliographic information in a text

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

    reference type or name

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.44
     ModelExpression
    -0.43
    Cyfarwyddwr
    -0.41
    KommentareTeilen
    -0.41
    PhysRevLett
    -0.40
     الحره
    -0.40
    :+:
    -0.40
     protoimpl
    -0.40
     Obrador
    -0.39
    Jîn
    -0.38
    POSITIVE LOGITS
    AndEndTag
    0.52
    tagHelperRunner
    0.49
    ValueStyle
    0.48
    findOneAndUpdate
    0.45
    úgó
    0.44
    səhifə
    0.43
    ähteet
    0.42
     Seitz
    0.42
     MenuView
    0.41
    brio
    0.41
    Act Density 1.043%

    No Known Activations