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

    Neuronpedia

    INDEX
    Explanations

    formula for combinations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Innen
    0.45
    José
    0.43
    তিকর
    0.40
    л
    0.38
     советы
    0.38
    нкү
    0.37
     વપરા
    0.37
    Hiro
    0.37
    ро
    0.37
    сад
    0.37
    POSITIVE LOGITS
     mengubah
    0.46
     decid
    0.45
     creating
    0.44
     hex
    0.44
     sebagian
    0.43
     barat
    0.43
     créer
    0.43
     rasa
    0.42
     berubah
    0.42
     vinyl
    0.41
    Act Density 0.003%

    No Known Activations