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

    Neuronpedia

    INDEX
    Explanations

    terms related to reversing or altering decisions or actions

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

    undoing, reverting, or rolling back

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    exitRule
    -0.35
     peruana
    -0.34
    ROIT
    -0.33
     Puedes
    -0.33
    An
    -0.33
     tutkim
    -0.32
    InitStruct
    -0.32
    ようになりました
    -0.32
     mikä
    -0.31
    makta
    -0.31
    POSITIVE LOGITS
     snippetHide
    0.77
     nonUne
    0.67
    intios
    0.62
    MigrationBuilder
    0.61
    تقاوى
    0.59
    Бахар
    0.59
    wapV
    0.54
    دانشنامهٔ
    0.54
     يتيمه
    0.53
     doInBackground
    0.52
    Act Density 0.001%

    No Known Activations