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

    Neuronpedia

    INDEX
    Explanations

    code/URLs/random strings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kite
    -0.07
     row
    -0.07
    身体
    -0.07
     kita
    -0.07
     arose
    -0.07
    Ý
    -0.07
    בתי
    -0.07
    ǜ
    -0.07
     simplify
    -0.07
    Ƙ
    -0.06
    POSITIVE LOGITS
    呼ばれ
    0.07
     Chrysler
    0.07
    调料
    0.07
    轮廓
    0.07
    供货
    0.07
    琫
    0.07
    油腻
    0.07
    Researchers
    0.06
     Chile
    0.06
    <stdlib
    0.06
    Act Density 0.096%

    No Known Activations