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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to scientific and historical contexts

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

    Danish and Latin terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Houſe
    -0.92
     Majefty
    -0.91
     Anſ
    -0.90
     houſe
    -0.89
     ſta
    -0.87
    ſelf
    -0.87
     pleaſure
    -0.85
     myſelf
    -0.85
     himſelf
    -0.84
     ſte
    -0.84
    POSITIVE LOGITS
    Notae
    0.43
    帖最后由
    0.42
     aceste
    0.40
     sementes
    0.39
     spalle
    0.38
     conclusiones
    0.38
     sécher
    0.38
     scuole
    0.38
     mármol
    0.38
     Margo
    0.37
    Act Density 0.061%

    No Known Activations