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

    Neuronpedia

    INDEX
    Explanations

    instances and concepts related to the act of reversing or undoing actions

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

    undo, reverse, repeal, vacate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     صوتيه
    -0.59
    AnchorStyles
    -0.54
    يكب
    -0.52
    -0.51
     propOrder
    -0.51
    цездатний
    -0.50
    лтамалар
    -0.50
     فريبيس
    -0.50
    yntaxException
    -0.49
    twimg
    -0.47
    POSITIVE LOGITS
     undo
    0.66
     undoing
    0.65
     Undo
    0.62
    Undo
    0.58
     reversal
    0.57
     reversing
    0.56
     reversed
    0.56
    undo
    0.48
     repeal
    0.47
     reversible
    0.46
    Act Density 0.278%

    No Known Activations