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

    Neuronpedia

    INDEX
    Explanations

    data identifiers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     youths
    -0.07
    .array
    -0.06
     glide
    -0.06
    šší
    -0.06
    (pop
    -0.06
    DataFrame
    -0.06
    walker
    -0.06
     đời
    -0.06
     fucking
    -0.06
    enne
    -0.06
    POSITIVE LOGITS
    ünü
    0.07
     unsupported
    0.06
     brides
    0.06
     Raleigh
    0.06
     Temmuz
    0.06
     поки
    0.06
    boro
    0.06
     sayılı
    0.06
     몰
    0.06
     ana
    0.06
    Act Density 0.013%

    No Known Activations