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
     zijn
    -0.08
     California
    -0.07
    acr
    -0.07
     eder
    -0.07
    California
    -0.07
    ossil
    -0.06
    ंगठन
    -0.06
    .Connect
    -0.06
    itational
    -0.06
    訂
    -0.06
    POSITIVE LOGITS
    fig
    0.06
    FAILED
    0.06
     ju
    0.06
    ))/(
    0.06
    。「
    0.06
    grunt
    0.06
    '])
↵
    0.06
    ?>>↵
    0.06
    leftright
    0.06
    ]}
    0.06
    Act Density 0.001%

    No Known Activations