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

    Neuronpedia

    INDEX
    Explanations

    key elements and confirmation requests in procedural or instructional text

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

    end of sentences with !!

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    matchCondition
    -0.46
    SharedDtor
    -0.45
    麽
    -0.43
    antoms
    -0.42
    }');
    -0.41
    AddTagHelper
    -0.40
    >';
    -0.39
    ViewFeatures
    -0.39
    UserScript
    -0.39
     thiệu
    -0.38
    POSITIVE LOGITS
     écrite
    0.42
     exemplified
    0.41
     dessinée
    0.41
     Durchsch
    0.41
     przes
    0.41
    vivencia
    0.41
    ształ
    0.40
     Besøkt
    0.39
    embolso
    0.39
    rildi
    0.39
    Act Density 0.216%

    No Known Activations