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

    Neuronpedia

    INDEX
    Explanations

    can

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     যদিও
    -0.09
     এছ
    -0.08
     চ
    -0.08
     প্রতিব
    -0.08
     সত
    -0.08
     мер
    -0.08
     বল
    -0.08
     বিজ্ঞ
    -0.08
     elä
    -0.08
     Fav
    -0.08
    POSITIVE LOGITS
     October
    0.09
    primer
    0.08
    සා
    0.08
     comienzo
    0.08
     travaille
    0.07
     José
    0.07
     ASAP
    0.07
     Tari
    0.07
     inevitable
    0.07
     poter
    0.07
    Act Density 0.012%

    No Known Activations