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

    Neuronpedia

    INDEX
    Explanations

    phone car integration

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _sy
    -0.07
    醇
    -0.07
    _rates
    -0.07
    rnd
    -0.07
     Estimated
    -0.07
    組�
    -0.07
    纠错
    -0.07
    收集
    -0.07
     QUICK
    -0.07
    grund
    -0.07
    POSITIVE LOGITS
     Sync
    0.07
     object
    0.07
    に入って
    0.07
     Furious
    0.06
    menu
    0.06
    五十
    0.06
    /C
    0.06
    using
    0.06
     ح
    0.06
     Muslims
    0.06
    Act Density 0.056%

    No Known Activations