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

    Neuronpedia

    INDEX
    Explanations

    patterns or structures resembling programming language syntax and operations

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

    Code, exceptions, and null values

    np_acts-logits-general · gemini-2.0-flash

    nothing or anything

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ostavi
    -0.72
    Revenir
    -0.71
    ToAction
    -0.71
    ChildScrollView
    -0.63
    alnız
    -0.59
     بيها
    -0.58
    newArrayList
    -0.58
    transQ
    -0.57
     مشين
    -0.56
     propOrder
    -0.55
    POSITIVE LOGITS
     nothing
    1.06
    nothing
    0.98
    Nothing
    0.94
     Nothing
    0.90
     anything
    0.89
     NOTHING
    0.87
     rien
    0.85
     nothin
    0.82
    Anything
    0.80
    anything
    0.80
    Act Density 0.058%

    No Known Activations