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

    Neuronpedia

    INDEX
    Explanations

    online medical advice and safety guidelines

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

    conditions and actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     NSCoder
    -0.42
    charCode
    -0.38
    ViewImports
    -0.36
     various
    -0.36
     sometimes
    -0.35
     jopa
    -0.35
     bazen
    -0.34
     niektor
    -0.33
    XtraReports
    -0.33
     several
    -0.33
    POSITIVE LOGITS
     للاسماء
    0.59
     незавершена
    0.59
    FunctionFlags
    0.55
     faſt
    0.54
     ſtate
    0.52
     ویکی‌پدی
    0.52
     autorytatywna
    0.51
     Monfieur
    0.50
     ModelExpression
    0.50
     noDo
    0.50
    Act Density 0.083%

    No Known Activations