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

    Neuronpedia

    INDEX
    Explanations

    nouns related to structural components or assemblies

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

    technical concepts and their properties

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.65
    Autoritní
    -0.58
    WriteTagHelper
    -0.56
    TagMode
    -0.55
    ----</
    -0.50
    Попис
    -0.50
    LookAnd
    -0.48
    "}";
    -0.47
     PeEnEo
    -0.47
     CreateTagHelper
    -0.46
    POSITIVE LOGITS
     wzglę
    0.53
     tatuagens
    0.52
     coroa
    0.50
     menyer
    0.49
     miniaturka
    0.49
     pensamentos
    0.48
     Woche
    0.48
     hoek
    0.47
     relatie
    0.45
     that
    0.45
    Act Density 0.352%

    No Known Activations