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

    Neuronpedia

    INDEX
    Explanations

    cities and countries

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    항
    -0.07
     По
    -0.07
    Mos
    -0.07
    蕴
    -0.07
    ทะ
    -0.07
     Gir
    -0.06
    鬧
    -0.06
     своем
    -0.06
    فرق
    -0.06
    Thunder
    -0.06
    POSITIVE LOGITS
     utilizando
    0.08
    (library
    0.07
    年由盛
    0.07
    *i
    0.06
     adalah
    0.06
    .Dark
    0.06
    (cookie
    0.06
     edi
    0.06
     środk
    0.06
     wat
    0.06
    Act Density 0.035%

    No Known Activations