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

    Neuronpedia

    INDEX
    Explanations

    -

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     תפ
    -0.07
    🍵
    -0.07
    福
    -0.06
    骗
    -0.06
    plugin
    -0.06
    チョ
    -0.06
    -wow
    -0.06
     ance
    -0.06
     Samsung
    -0.06
    Santa
    -0.06
    POSITIVE LOGITS
     lý
    0.07
    裏
    0.07
    .Non
    0.07
    这里面
    0.07
    roker
    0.07
    أشياء
    0.07
     ----------
    0.07
     gameObject
    0.07
     Conference
    0.06
    	Created
    0.06
    Act Density 0.010%

    No Known Activations