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

    Neuronpedia

    INDEX
    Explanations

    references to specific data structures and computational tests

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

    numbers and equations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Administrativna
    -0.88
     AssemblyCulture
    -0.74
     <>",
    -0.73
    rungsseite
    -0.69
     fieldNum
    -0.68
    <unused16>
    -0.68
    <unused41>
    -0.68
    <unused17>
    -0.67
    <unused14>
    -0.67
    <unused8>
    -0.67
    POSITIVE LOGITS
    ↵↵
    0.36
    生
    0.29
     associated
    0.29
     стоит
    0.29
    <h1>
    0.29
     af
    0.28
    比
    0.28
    ServiceModel
    0.28
     Issue
    0.27
     הד
    0.27
    Act Density 0.088%

    No Known Activations