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

    Neuronpedia

    INDEX
    Explanations

    occurrences of code snippets and function definitions

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

    start of user turn

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ConstraintMaker
    -0.73
    Personendaten
    -0.70
    GEBURTSDATUM
    -0.69
    Tikang
    -0.66
     kaarangay
    -0.66
    CloseOperation
    -0.64
    SourceChecksum
    -0.63
     oprot
    -0.62
     queſta
    -0.61
    SharedDtor
    -0.61
    POSITIVE LOGITS
     our
    0.54
     various
    0.48
     the
    0.47
    listdir
    0.45
     tak
    0.45
     members
    0.42
     elements
    0.40
     knowledge
    0.39
    our
    0.39
     several
    0.38
    Act Density 0.001%

    No Known Activations