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

    Neuronpedia

    INDEX
    Explanations

    instances of exceptions or error handling in code

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

    safety analysis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kasarigan
    -0.54
    withOpacity
    -0.52
    ⇝
    -0.51
    ThemeOverlay
    -0.50
     للاسماء
    -0.45
     typelib
    -0.44
     '\\;'
    -0.44
    ➌
    -0.43
     propOrder
    -0.42
     مرئيه
    -0.42
    POSITIVE LOGITS
    الحياه
    0.61
     /\.(
    0.54
     /\.
    0.44
     Masyarakat
    0.40
    Pozri
    0.39
     fatta
    0.39
    clerView
    0.36
     <<<<<<<<<<<<<<
    0.36
    Iné
    0.36
    见状
    0.35
    Act Density 0.001%

    No Known Activations