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

    Neuronpedia

    INDEX
    Explanations

    A

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ât
    -0.08
     continue
    -0.07
     하나님의
    -0.07
    target
    -0.07
    rö
    -0.07
    有不同的
    -0.07
     similarly
    -0.07
     tạo
    -0.07
    希望通过
    -0.07
     통해서
    -0.07
    POSITIVE LOGITS
    �
    0.07
     unit
    0.07
    开关
    0.07
    内存
    0.07
    (plugin
    0.07
    ainers
    0.06
    şi
    0.06
     multic
    0.06
     כניסה
    0.06
    -The
    0.06
    Act Density 0.020%

    No Known Activations