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
     מציע
    -0.08
     pragmatic
    -0.07
     expectation
    -0.07
     embarrassment
    -0.07
    .InputStreamReader
    -0.07
     <=>
    -0.07
    VISION
    -0.07
     asphalt
    -0.07
     prima
    -0.07
    -win
    -0.07
    POSITIVE LOGITS
     Duke
    0.07
    anted
    0.07
     circ
    0.07
    叔叔
    0.07
     digit
    0.07
     sensors
    0.07
     nig
    0.06
     deque
    0.06
    柚
    0.06
    cerer
    0.06
    Act Density 0.000%

    No Known Activations