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

    Neuronpedia

    INDEX
    Explanations

    1

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     waktu
    -0.08
    _sg
    -0.08
     sistem
    -0.07
    .events
    -0.07
    Ti
    -0.07
    rai
    -0.07
    万事
    -0.07
    퀴
    -0.07
    iks
    -0.07
     bev
    -0.07
    POSITIVE LOGITS
    掴
    0.08
    <&
    0.08
     ]↵
    0.07
    ]]:↵
    0.07
    ]]↵
    0.07
    '));↵
    0.07
     *__
    0.07
    \",↵
    0.07
     fingertips
    0.07
    '])↵
    0.07
    Act Density 0.001%

    No Known Activations