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

    Neuronpedia

    INDEX
    Explanations

    should

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    唱
    -0.06
    貨
    -0.06
    (strip
    -0.06
    _gem
    -0.06
    人人
    -0.06
    谁
    -0.06
     chế
    -0.06
    .parseDouble
    -0.06
     tarih
    -0.06
    ンパ
    -0.06
    POSITIVE LOGITS
    �
    0.07
    .cm
    0.06
     вкус
    0.06
    광역시
    0.06
     máme
    0.06
     consuming
    0.06
     nhưng
    0.06
    emu
    0.06
     occured
    0.06
    hi
    0.06
    Act Density 0.020%

    No Known Activations