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

    Neuronpedia

    INDEX
    Explanations

    references to figures or diagrams in the text

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

    figure references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     المعيارى
    -0.51
    NameInMap
    -0.51
    HideFlags
    -0.49
     >=",
    -0.49
     AssemblyCompany
    -0.45
    حياتها
    -0.44
    :+:
    -0.43
     otomatig
    -0.43
     الرياضيه
    -0.42
    PreferredItem
    -0.42
    POSITIVE LOGITS
    OptionsMenu
    0.46
    components
    0.46
     utilities
    0.45
     colours
    0.44
     تانيه
    0.44
    styles
    0.44
     widgets
    0.44
    انتهای
    0.44
     Det
    0.43
    PONENTS
    0.43
    Act Density 0.001%

    No Known Activations