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

    Neuronpedia

    INDEX
    Explanations

    specific programming structures or data types in code

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

    mathematical notation and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    httphttps
    -1.20
     surla
    -1.05
    <unused41>
    -1.05
    [@BOS@]
    -1.04
    <unused52>
    -1.04
    <unused14>
    -1.04
    <unused43>
    -1.04
    <unused28>
    -1.04
    <unused3>
    -1.04
    <unused8>
    -1.04
    POSITIVE LOGITS
    <h1>
    0.40
    A
    0.36
    T
    0.34
    B
    0.34
    /*
    0.33
    <strong>
    0.33
    I
    0.33
    <b>
    0.32
    M
    0.31
    Q
    0.30
    Act Density 0.024%

    No Known Activations