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

    Neuronpedia

    INDEX
    Explanations

    references to leaks or leaking information

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

    leak or leakage of information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     CommandType
    -0.54
     functools
    -0.52
     numberWith
    -0.50
    opsida
    -0.49
    ptonshire
    -0.47
    CommandType
    -0.47
    atoday
    -0.47
    RectangleBorder
    -0.45
     Bons
    -0.44
    msen
    -0.44
    POSITIVE LOGITS
     leak
    1.16
    Leak
    1.14
     Leak
    1.14
    leak
    1.13
     leaks
    1.03
     Leaks
    0.96
     Leakage
    0.94
     leakage
    0.93
     leaking
    0.91
     leaked
    0.88
    Act Density 0.009%

    No Known Activations