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

    Neuronpedia

    INDEX
    Explanations

    written content

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	X
    -0.07
     Table
    -0.07
     BH
    -0.07
     detects
    -0.07
     MY
    -0.07
    tasks
    -0.07
    라이
    -0.06
    _DAY
    -0.06
     BST
    -0.06
    ันทร
    -0.06
    POSITIVE LOGITS
     zákona
    0.07
    �
    0.07
    astered
    0.06
     magna
    0.06
    ุงเทพมหานคร
    0.06
    搬
    0.06
     *@
    0.06
     Đề
    0.06
    .handleSubmit
    0.06
     //!↵
    0.06
    Act Density 0.142%

    No Known Activations