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

    Neuronpedia

    INDEX
    Explanations

    numerical or ordinal references in the context of structured information

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

    specific structural references within a document, particularly related to numbered sections or entries

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

    ordinal numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Gambas
    -0.56
     către
    -0.55
    IUrlHelper
    -0.55
     fumée
    -0.52
     preferido
    -0.52
     okuyayım
    -0.51
    anho
    -0.51
     saites
    -0.51
     inoxydable
    -0.51
     stră
    -0.50
    POSITIVE LOGITS
     two
    1.15
    two
    0.84
    TagMode
    0.82
     three
    0.78
     deux
    0.74
     half
    0.68
    MessageTagHelper
    0.67
     beiden
    0.67
    SourceChecksum
    0.67
     part
    0.66
    Act Density 0.113%

    No Known Activations