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

    Neuronpedia

    INDEX
    Explanations

    proper nouns and specific names within the text

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

    place names and surnames

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    horabuena
    -0.52
     enfans
    -0.49
     Gedicht
    -0.45
     Grecs
    -0.44
     griech
    -0.44
     Grèce
    -0.43
     mencer
    -0.42
     Arzne
    -0.41
    vänt
    -0.41
     betyr
    -0.41
    POSITIVE LOGITS
     Salle
    1.29
     Wakefield
    1.11
    Salle
    0.97
     LaSalle
    0.92
     Mansfield
    0.89
    intree
    0.67
    salle
    0.65
     Barton
    0.62
     salle
    0.59
    Barton
    0.58
    Act Density 0.006%

    No Known Activations