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

    Neuronpedia

    INDEX
    Explanations

    CONFIG

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _instr
    -0.09
     teslim
    -0.09
    andır
    -0.08
     attorney
    -0.08
    েয়ে
    -0.08
     আক্রান্ত
    -0.07
    ั้น
    -0.07
     বাহ
    -0.07
     sull
    -0.07
    배송
    -0.07
    POSITIVE LOGITS
     Arts
    0.10
     arts
    0.08
     submenu
    0.08
    .checkbox
    0.08
    કા
    0.08
    Arts
    0.08
     Constitutional
    0.08
     منتخب
    0.08
    خاب
    0.08
     Inde
    0.08
    Act Density 0.002%

    No Known Activations