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

    Neuronpedia

    INDEX
    Explanations

    specific characters or symbols used in programming or markup languages

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

    periods followed by letters or numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     queſta
    -0.86
    ſſung
    -0.84
    <unused51>
    -0.82
    [@BOS@]
    -0.82
    <unused3>
    -0.82
    <unused32>
    -0.81
    <unused41>
    -0.81
    <unused28>
    -0.81
    <unused8>
    -0.81
    <unused16>
    -0.81
    POSITIVE LOGITS
    <h2>
    0.45
    ↵
    0.43
     
    0.42
    </h3>
    0.42
    <h1>
    0.42
    <h3>
    0.41
    </h1>
    0.41
    </u>
    0.40
    </strong>
    0.39
     `
    0.39
    Act Density 0.017%

    No Known Activations