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

    Neuronpedia

    INDEX
    Explanations

    code-related terms and functions used in programming or pattern matching

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

    replace text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     BorderSide
    -0.56
    parsedMessage
    -0.56
    Życiorys
    -0.55
     queſta
    -0.55
    ௃
    -0.54
     Djibouti
    -0.54
     ſeyn
    -0.53
    𑄥
    -0.53
    ſicht
    -0.53
     contextLoads
    -0.53
    POSITIVE LOGITS
    Personendaten
    0.34
    MLLoader
    0.33
    outer
    0.31
     trace
    0.29
    цезда
    0.29
    bag
    0.29
     Gee
    0.29
     Trace
    0.29
     bag
    0.28
    ię
    0.28
    Act Density 0.116%

    No Known Activations