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

    Neuronpedia

    INDEX
    Explanations

    terms related to reverting or undoing actions

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

    rollback or scrapbook background

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fallu
    -0.40
    Sire
    -0.39
    Hem
    -0.38
    ="@+
    -0.36
    InSection
    -0.35
    Daz
    -0.34
    Aqu
    -0.34
     onData
    -0.33
    เจ
    -0.32
    Neb
    -0.31
    POSITIVE LOGITS
    rollback
    2.44
    Rollback
    2.03
     rollback
    2.00
    revert
    0.71
    printStackTrace
    0.65
    Flashback
    0.64
     onFailure
    0.64
     undo
    0.62
    traceback
    0.61
     traceback
    0.60
    Act Density 0.001%

    No Known Activations