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

    Neuronpedia

    INDEX
    Explanations

    references to locations or settings within the text

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

    dans (location/containment)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ⟬
    -0.72
     müſſen
    -0.68
    出版年
    -0.65
     propOrder
    -0.63
    AddTagHelper
    -0.62
     laſſen
    -0.62
    findpost
    -0.62
     kasarigan
    -0.60
    unknownFields
    -0.60
     awakeFromNib
    -0.58
    POSITIVE LOGITS
     dans
    0.72
    Dans
    0.60
     Dans
    0.60
     trong
    0.59
     dalam
    0.58
     DANS
    0.57
     inside
    0.56
     in
    0.54
     Nella
    0.54
     within
    0.52
    Act Density 0.002%

    No Known Activations