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

    Neuronpedia

    INDEX
    Explanations

    squares

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Hawaii
    -0.07
    $user
    -0.07
     Iris
    -0.07
     ON
    -0.06
    Legal
    -0.06
     authenticate
    -0.06
     authentication
    -0.06
     Degree
    -0.06
    Pause
    -0.06
    user
    -0.06
    POSITIVE LOGITS
    álním
    0.06
     sö
    0.06
     컨
    0.06
     alcan
    0.06
     inherently
    0.06
     برابر
    0.06
    例
    0.06
     Solver
    0.06
     ils
    0.06
     œ
    0.06
    Act Density 0.012%

    No Known Activations