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

    Neuronpedia

    INDEX
    Explanations

    down

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tín
    -0.07
     basket
    -0.07
    ерта
    -0.06
     door
    -0.06
    	rb
    -0.06
     palabras
    -0.06
     medals
    -0.06
     drawer
    -0.06
    敬
    -0.06
     Hoa
    -0.06
    POSITIVE LOGITS
    鸡
    0.07
    omitempty
    0.07
    Settings
    0.06
    різ
    0.06
    हर
    0.06
    _BLE
    0.06
    stroke
    0.06
     Gaga
    0.06
    ประถม
    0.06
    =color
    0.06
    Act Density 0.163%

    No Known Activations