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

    Neuronpedia

    INDEX
    Explanations

    instances of numerical data or values in the text

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

    code keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     rapidly
    -0.33
     rápidas
    -0.33
     quickly
    -0.33
    <strong>
    -0.31
     periódicos
    -0.31
    <em>
    -0.30
     pocos
    -0.29
     carefully
    -0.29
    <eos>
    -0.28
     quick
    -0.28
    POSITIVE LOGITS
    SequentialGroup
    0.92
    UnusedPrivate
    0.91
    帖最后由
    0.89
    tagHelperRunner
    0.79
    OGND
    0.76
     ब्रेकडाउन
    0.75
    Personendaten
    0.74
    MemoryWarning
    0.73
    [@BOS@]
    0.72
    <unused3>
    0.71
    Act Density 0.020%

    No Known Activations