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

    Neuronpedia

    INDEX
    Explanations

    programming-related terms and structures

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

    official language processing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    TagHelper
    -0.57
    GEBURTSDATUM
    -0.56
    ValueStyle
    -0.52
    Personendaten
    -0.52
    GraphicsUnit
    -0.52
     CommandType
    -0.52
    новниш
    -0.50
    MockBean
    -0.48
     صوتيه
    -0.47
    ScopeManager
    -0.47
    POSITIVE LOGITS
     complete
    0.46
     official
    0.41
     propios
    0.40
     pagrind
    0.40
     hard
    0.38
     nationales
    0.38
     ufficiali
    0.38
     offizi
    0.38
    official
    0.37
     komplette
    0.36
    Act Density 0.003%

    No Known Activations