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

    Neuronpedia

    INDEX
    Explanations

    Foreign languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     wreck
    -0.07
     pegg
    -0.07
     repart
    -0.07
     Nem
    -0.07
     pe
    -0.07
    จัด
    -0.07
     ek
    -0.07
     Solo
    -0.07
    गार
    -0.07
    ök
    -0.07
    POSITIVE LOGITS
    乾
    0.08
     locom
    0.07
     nations
    0.07
    Dav
    0.07
    FACT
    0.07
     cultures
    0.07
    েত
    0.07
     mara
    0.07
     diffraction
    0.07
     Leuk
    0.07
    Act Density 0.219%

    No Known Activations