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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "de" as well as variations or derivations of it

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

    de, the, and foreign articles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.90
    piram
    -0.77
    存于互联网档案馆
    -0.75
     Wikiseite
    -0.73
    httphttps
    -0.71
     للاسماء
    -0.69
     дописавши
    -0.68
    UnknownFieldSet
    -0.67
    setVerticalGroup
    -0.66
    AutoScaleMode
    -0.65
    POSITIVE LOGITS
    The
    0.79
     the
    0.78
     The
    0.75
     de
    0.69
    the
    0.66
    Οι
    0.60
     οι
    0.59
     their
    0.58
     ihre
    0.57
     der
    0.56
    Act Density 0.000%

    No Known Activations