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

    Neuronpedia

    INDEX
    Explanations

    number

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    isoft
    -0.07
    鋼
    -0.07
     kia
    -0.07
     благ
    -0.06
     amort
    -0.06
     Shed
    -0.06
     Sour
    -0.06
    	xml
    -0.06
     Breakfast
    -0.06
    mighty
    -0.06
    POSITIVE LOGITS
    ='./
    0.06
    ueue
    0.06
     belongings
    0.06
    rib
    0.06
    .Floor
    0.06
     Fuji
    0.06
    soever
    0.05
    _bindings
    0.05
    {}\
    0.05
    mainwindow
    0.05
    Act Density 0.013%

    No Known Activations