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

    Neuronpedia

    INDEX
    Explanations

    we

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     flair
    -0.07
    print
    -0.07
    ____
    -0.06
    jím
    -0.06
    :>
    -0.06
     refined
    -0.06
    Ey
    -0.06
    кус
    -0.06
    ै।
    -0.06
    tile
    -0.06
    POSITIVE LOGITS
     "+↵
    0.06
    (sin
    0.06
    +"_
    0.06
    abouts
    0.06
    +'_
    0.06
     Denied
    0.06
     Sioux
    0.06
    'field
    0.06
    	NdrFcShort
    0.06
     información
    0.06
    Act Density 0.149%

    No Known Activations