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

    Neuronpedia

    INDEX
    Explanations

    ore

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ('\\
    -0.07
    292
    -0.07
    'a
    -0.07
    446
    -0.07
    на
    -0.06
     Azerbai
    -0.06
    isations
    -0.06
    "*
    -0.06
     вуз
    -0.06
    ВА
    -0.06
    POSITIVE LOGITS
    ichern
    0.07
     зер
    0.07
    London
    0.07
    .sorted
    0.07
    elerinden
    0.06
     tones
    0.06
     Wireless
    0.06
    	win
    0.06
     JOHN
    0.06
     Clerk
    0.06
    Act Density 0.004%

    No Known Activations