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

    Neuronpedia

    INDEX
    Explanations

    file path or directory references in code

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

    relative path traversals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .
    -0.34
     
    -0.30
     des
    -0.27
    (&:
    -0.27
     tri
    -0.25
     est
    -0.25
    ️
    -0.25
    void
    -0.24
    )
    -0.24
    </strong>
    -0.24
    POSITIVE LOGITS
    parsedMessage
    0.87
    OGND
    0.87
     للاسماء
    0.85
    <unused3>
    0.82
    <unused23>
    0.82
    <unused1>
    0.82
    <unused8>
    0.82
    <unused41>
    0.82
    [@BOS@]
    0.81
    <unused16>
    0.81
    Act Density 0.001%

    No Known Activations