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

    Neuronpedia

    INDEX
    Explanations

    :name

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     prowess
    -0.08
    entence
    -0.07
     דואר
    -0.07
     cheeses
    -0.07
    (Qt
    -0.07
     PRE
    -0.07
     Bruce
    -0.07
    промыш
    -0.07
     Người
    -0.07
     brief
    -0.07
    POSITIVE LOGITS
    YSTICK
    0.07
     ske
    0.07
    _chunks
    0.07
     originals
    0.07
    	Delete
    0.07
     dealloc
    0.06
     Deploy
    0.06
    utches
    0.06
     fw
    0.06
    -roll
    0.06
    Act Density 0.000%

    No Known Activations