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

    Neuronpedia

    INDEX
    Explanations

    frequent use of punctuation in code snippets and the manipulation of string values

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

    Code-related punctuation

    np_acts-logits-general · gemini-2.0-flash

    code and data parsing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    XmlAccessType
    -0.56
     तो
    -0.55
     GenerationType
    -0.53
    onAttach
    -0.50
    entitled
    -0.49
    Intent
    -0.45
    diri
    -0.45
    новништво
    -0.44
     onCancelled
    -0.44
    HasIndex
    -0.44
    POSITIVE LOGITS
     nahilalakip
    0.65
    verwijspagina
    0.65
    ondissement
    0.62
    脚注の使い方
    0.59
    istoitu
    0.58
    saraba
    0.57
     unknownFields
    0.57
    uxxxx
    0.57
    Portail
    0.56
     omge
    0.53
    Act Density 0.102%

    No Known Activations