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

    Neuronpedia

    INDEX
    Explanations

    we

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    upload
    -0.07
     CURRENT
    -0.06
     priest
    -0.06
    $log
    -0.06
    $mail
    -0.06
     Tên
    -0.06
    ̣
    -0.06
    Pří
    -0.06
     REQUIRE
    -0.06
    .’”↵↵
    -0.06
    POSITIVE LOGITS
     Fl
    0.07
    (changes
    0.07
     आकर
    0.07
     利
    0.06
    Enumerable
    0.06
     front
    0.06
    ateau
    0.06
    acebook
    0.06
     instancia
    0.06
    τσ
    0.06
    Act Density 0.027%

    No Known Activations