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

    Neuronpedia

    INDEX
    Explanations

    frequent pronouns and expressions of agreement or acknowledgment

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

    common phrases and programming terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Véxase
    -0.47
     ब्रेकडाउन
    -0.45
    — 
    -0.44
    BindingResult
    -0.40
     impro
    -0.40
     rowCount
    -0.39
    ValueStyle
    -0.39
     ReSharper
    -0.38
     beina
    -0.38
     _)
    -0.38
    POSITIVE LOGITS
     '\\;'
    0.59
    InjectAttribute
    0.59
    SharedDtor
    0.54
     gustado
    0.50
     käytt
    0.50
     asesinado
    0.49
     transfieras
    0.47
    UrlResolution
    0.45
    PropertyChanging
    0.45
    clable
    0.43
    Act Density 0.124%

    No Known Activations