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

    Neuronpedia

    INDEX
    Explanations

    past

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    精品
    -0.07
     Pause
    -0.07
     состояние
    -0.07
     José
    -0.06
     населения
    -0.06
     frais
    -0.06
    碧
    -0.06
     محمد
    -0.06
    äßig
    -0.06
    为您提供
    -0.06
    POSITIVE LOGITS
    Symbols
    0.08
    Ẳ
    0.07
     의사
    0.07
    干事
    0.07
     JFactory
    0.07
     일을
    0.07
    Isl
    0.07
     ultr
    0.07
    سقط
    0.07
    为例
    0.07
    Act Density 0.037%

    No Known Activations