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

    Neuronpedia

    INDEX
    Explanations

    code-related syntax or keywords used in programming languages

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

    special characters and code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     keten
    -0.36
    StructEnd
    -0.36
    AnchorTagHelper
    -0.35
    ajax
    -0.35
    Bilan
    -0.34
    ore
    -0.34
    te
    -0.34
     kör
    -0.33
    iega
    -0.33
     law
    -0.32
    POSITIVE LOGITS
     Италијани
    0.84
     <<<<<<<<<<<<<<
    0.72
     nakalista
    0.64
    DoubleQuotes
    0.60
     ſind
    0.57
    tvguidetime
    0.57
    الحياه
    0.57
    цездатний
    0.57
    GOTREF
    0.55
    يكب
    0.54
    Act Density 0.001%

    No Known Activations