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

    Neuronpedia

    INDEX
    Explanations

    code-related constructs and syntax elements

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

    XML closing tags, code syntax, multilingual text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    oneofs
    -0.56
    Попис
    -0.54
     possessive
    -0.50
    Abitanti
    -0.50
    Carriera
    -0.48
    SharedCtor
    -0.48
    Abit
    -0.47
    ########.
    -0.46
    GEBURTSDATUM
    -0.46
    BufferException
    -0.45
    POSITIVE LOGITS
    transQ
    0.54
    Entra
    0.42
     Waray
    0.39
     ympä
    0.39
     OnTrigger
    0.39
    ptăm
    0.36
     dichiarato
    0.36
     julk
    0.36
     työn
    0.35
    erintah
    0.35
    Act Density 0.001%

    No Known Activations