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

    Neuronpedia

    INDEX
    Explanations

    phrases related to programming logic and code structure

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

    French, Spanish, or Portuguese words

    np_acts-logits-general · gemini-2.0-flash

    prepositions and articles in Romance languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    @[+][
    -0.95
     متعلقه
    -0.92
     <=",
    -0.90
     snippetHide
    -0.88
     ujednoznacz
    -0.85
     שוליים
    -0.85
     intptr
    -0.85
     quæ
    -0.83
     Taktlose
    -0.83
    Personensuche
    -0.82
    POSITIVE LOGITS
     del
    0.67
     dell
    0.58
     des
    0.55
     della
    0.55
     dels
    0.52
     du
    0.51
     delle
    0.51
     de
    0.49
    '
    0.46
     
    0.43
    Act Density 0.087%

    No Known Activations