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

    Neuronpedia

    INDEX
    Explanations

    code constructs related to error handling and response management

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

    code keywords and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MessageOf
    -0.40
    dafx
    -0.38
     Italijani
    -0.38
    mær
    -0.30
    jspb
    -0.30
     kaarangay
    -0.29
    uxxxx
    -0.29
     rencontr
    -0.29
    initializeApp
    -0.28
    -0.28
    POSITIVE LOGITS
    ዡ
    0.63
     Hilbert
    0.63
    〮
    0.62
     Solaris
    0.60
    <unused79>
    0.60
    <unused43>
    0.60
    <unused14>
    0.60
    <unused16>
    0.60
    <unused8>
    0.60
    [@BOS@]
    0.60
    Act Density 0.002%

    No Known Activations