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

    Neuronpedia

    INDEX
    Explanations

    elements related to command line options and arguments in programming contexts

    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
    toMatchSnapshot
    -0.35
    hichever
    -0.35
    ślę
    -0.34
    PrototypeOf
    -0.33
     segments
    -0.33
     contracts
    -0.32
    <&
    -0.32
    FORME
    -0.32
    NewReader
    -0.32
     regions
    -0.31
    POSITIVE LOGITS
     disambiguazione
    0.79
    NameInMap
    0.67
     utafitiHapana
    0.65
    MemoryWarning
    0.59
    Біографія
    0.59
    MessageOf
    0.57
    parsedMessage
    0.57
     Taktlose
    0.56
    UnusedPrivate
    0.56
    Microkernel
    0.55
    Act Density 0.003%

    No Known Activations