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

    Neuronpedia

    INDEX
    Explanations

    attributes related to cleanliness and clarity in various contexts

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

    clean or clear qualities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    richTextPanel
    -0.47
     invokingState
    -0.41
     الرياضيه
    -0.38
    RegistryLite
    -0.36
     незавершена
    -0.36
    etary
    -0.36
    CppMethod
    -0.35
    Enllaces
    -0.34
    이션
    -0.34
     Anlass
    -0.34
    POSITIVE LOGITS
     clean
    1.11
     clear
    1.11
     Clear
    1.00
     Clean
    1.00
    clean
    0.98
    clear
    0.97
    Clean
    0.96
     CLEAN
    0.95
    Clear
    0.94
     cleanly
    0.93
    Act Density 0.065%

    No Known Activations