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

    Neuronpedia

    INDEX
    Explanations

    structured data formats, particularly in programming and software development contexts

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

    create exponential distribution

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     finalmente
    -0.34
     наконец
    -0.30
     endlich
    -0.30
    SequentialGroup
    -0.29
     '
    -0.27
    finally
    -0.26
     finally
    -0.26
     incluyendo
    -0.25
     "
    -0.25
     Finalmente
    -0.24
    POSITIVE LOGITS
     パンチラ
    0.76
    <unused28>
    0.75
    <unused52>
    0.75
    [@BOS@]
    0.75
    <unused41>
    0.75
    <unused43>
    0.74
    <unused47>
    0.74
    <unused23>
    0.74
    <unused14>
    0.74
    <unused17>
    0.74
    Act Density 0.761%

    No Known Activations