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

    Neuronpedia

    INDEX
    Explanations

    phrases that involve the act of performing tasks or actions

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

    perform actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    niosek
    -0.52
     subsidy
    -0.51
    randomUUID
    -0.50
    "$_
    -0.49
     cadeaux
    -0.49
     Botschaft
    -0.49
    splitter
    -0.48
     haters
    -0.47
     Öffentlichkeit
    -0.47
     gulls
    -0.47
    POSITIVE LOGITS
     perform
    1.06
     Perform
    1.02
    perform
    1.01
     performed
    0.98
    Perform
    0.98
     performs
    0.92
     PERFORM
    0.88
     performing
    0.86
     Performed
    0.86
    performed
    0.80
    Act Density 0.027%

    No Known Activations