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

    Neuronpedia

    INDEX
    Explanations

    locations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Hist
    -0.06
     Corbyn
    -0.06
    gett
    -0.06
    (targetEntity
    -0.06
     chỉnh
    -0.06
     Sexual
    -0.06
     먼
    -0.06
    go
    -0.06
     για
    -0.05
    され
    -0.05
    POSITIVE LOGITS
    PyObject
    0.07
    ActionCode
    0.07
     ThreadPool
    0.07
    kám
    0.06
     Libert
    0.06
     тут
    0.06
    励
    0.06
    	SDL
    0.06
    Checkout
    0.06
     Code
    0.06
    Act Density 0.057%

    No Known Activations