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

    Neuronpedia

    INDEX
    Explanations

    code snippets and their associated issues or fixes

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

    code actions and results

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    parsedMessage
    -0.80
     témoig
    -0.76
    <unused8>
    -0.74
    [@BOS@]
    -0.74
    <unused16>
    -0.74
    <unused23>
    -0.74
    <unused51>
    -0.74
    <unused74>
    -0.74
    <unused3>
    -0.73
    <unused14>
    -0.73
    POSITIVE LOGITS
     Mo
    0.31
     mo
    0.30
     lui
    0.29
     …
    0.29
     ihn
    0.28
     fa
    0.28
     mga
    0.28
     
    0.28
     Mat
    0.27
    cy
    0.27
    Act Density 0.485%

    No Known Activations