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

    Neuronpedia

    INDEX
    Explanations

    Code and foreign languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Mixer
    -0.06
    -cache
    -0.06
    .ShouldBe
    -0.06
     fid
    -0.06
    -Fi
    -0.06
     endpoints
    -0.06
    .prepend
    -0.06
    shutdown
    -0.06
     thanh
    -0.06
    见
    -0.06
    POSITIVE LOGITS
    engineering
    0.06
    раниц
    0.06
    (hObject
    0.06
     التج
    0.06
     ре
    0.06
    ağ
    0.06
     게임
    0.06
     BCHP
    0.06
     Italians
    0.06
    ]));
    0.06
    Act Density 0.070%

    No Known Activations