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

    Neuronpedia

    INDEX
    Explanations

    programming commands and function calls within code snippets

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

    do, doing, done

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SpringRunner
    -0.46
     bénévoles
    -0.44
    gangssprach
    -0.43
     inoxydable
    -0.41
     fût
    -0.40
    agaimana
    -0.40
     skick
    -0.39
     desapar
    -0.39
     conoci
    -0.38
    DESTROY
    -0.38
    POSITIVE LOGITS
     done
    0.75
    done
    0.71
     do
    0.71
     Done
    0.71
    doing
    0.68
     DONE
    0.68
     doing
    0.68
     DO
    0.66
     Do
    0.66
     Doing
    0.65
    Act Density 0.049%

    No Known Activations