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

    Neuronpedia

    INDEX
    Explanations

    code/programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ผ
    -0.08
    lag
    -0.08
    (a
    -0.07
     spor
    -0.07
     pune
    -0.07
    回复
    -0.07
     correcting
    -0.07
     waste
    -0.07
     lag
    -0.07
    .misc
    -0.07
    POSITIVE LOGITS
    க்கும்
    0.08
     embarrassing
    0.07
     так
    0.07
     Reno
    0.07
     Lust
    0.07
    gay
    0.07
     teardown
    0.07
    0.07
     гэт
    0.07
     ">↵
    0.07
    Act Density 1.029%

    No Known Activations