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

    Neuronpedia

    INDEX
    Explanations

    di

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     RW
    -0.07
    zeigt
    -0.07
     Naw
    -0.07
     Rental
    -0.06
    -shot
    -0.06
     Tuy
    -0.06
    시오
    -0.06
     Chun
    -0.06
    參
    -0.06
     MAY
    -0.06
    POSITIVE LOGITS
    dad
    0.07
    .IsMatch
    0.07
    InProgress
    0.07
     доме
    0.07
    альные
    0.06
    ımı
    0.06
     pc
    0.06
    iline
    0.06
    шие
    0.06
     grandmother
    0.06
    Act Density 0.050%

    No Known Activations