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

    Neuronpedia

    INDEX
    Explanations

    instances of double underscores, typically indicating potential issues with buffer overflows in C programming

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

    <start_of_turn> user

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AndEndTag
    -0.68
     للاسماء
    -0.64
    SourceChecksum
    -0.60
    sizeCache
    -0.60
    enderror
    -0.60
     ***!
    -0.54
    Personensuche
    -0.50
    expandindo
    -0.49
     CreateTagHelper
    -0.49
    errHandler
    -0.48
    POSITIVE LOGITS
    TestTools
    0.89
    Референце
    0.89
     plufieurs
    0.50
    alakip
    0.47
    frc
    0.43
    ToAction
    0.43
     sartén
    0.42
     deſt
    0.42
    Referensi
    0.38
    ActionCreators
    0.38
    Act Density 0.001%

    No Known Activations