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

    Neuronpedia

    INDEX
    Explanations

    specific numerical codes or identifiers, likely related to legal or formal documents

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

    case numbers, grants, court dockets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <pad>
    -0.94
    <unused52>
    -0.94
    <unused16>
    -0.94
    <unused74>
    -0.94
    <unused23>
    -0.94
    <unused43>
    -0.93
    <unused79>
    -0.93
    <unused28>
    -0.93
    <unused68>
    -0.93
    [@BOS@]
    -0.93
    POSITIVE LOGITS
    <eos>
    0.34
    <h2>
    0.28
    0.28
    //
    0.27
    Và
    0.27
    Xna
    0.26
    енча
    0.26
    Ex
    0.26
    <h3>
    0.26
    <h1>
    0.25
    Act Density 0.072%

    No Known Activations