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

    Neuronpedia

    INDEX
    Explanations

    key mathematical and programming concepts, particularly related to conditional structures and types

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

    mathematical notation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ModelExpression
    -0.94
     '\\;'
    -0.85
    RenderAtEndOf
    -0.84
    IntoConstraints
    -0.84
     referrerpolicy
    -0.81
    httphttps
    -0.77
     ujednoznacz
    -0.74
     EconPapers
    -0.74
     AssemblyCulture
    -0.73
    hyrchwyd
    -0.73
    POSITIVE LOGITS
     to
    0.24
    Use
    0.24
    hawatir
    0.23
     trampa
    0.23
     so
    0.23
     kể
    0.23
      
    0.23
     antemano
    0.23
    ↵
    0.22
    Materials
    0.22
    Act Density 0.324%

    No Known Activations