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

    Neuronpedia

    INDEX
    Explanations

    code and data fragments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Yorker
    -0.07
     rentrer
    -0.07
    geo
    -0.07
     এমন
    -0.07
     definida
    -0.07
     REALTORS
    -0.07
     Gener
    -0.07
     تأس
    -0.07
     Senator
    -0.07
     তাদের
    -0.07
    POSITIVE LOGITS
     wait
    0.08
    .Pr
    0.08
    孟
    0.07
     kvinne
    0.07
    'A
    0.07
    yň
    0.07
    ാമ
    0.07
     teilweise
    0.07
     contr
    0.07
    _Pr
    0.07
    Act Density 0.351%

    No Known Activations