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

    Neuronpedia

    INDEX
    Explanations

    C

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    雷达
    -0.08
     ++$
    -0.07
    =edge
    -0.07
    조
    -0.07
     relieve
    -0.07
     А
    -0.07
     trạng
    -0.07
     typeof
    -0.06
     كتاب
    -0.06
    ياة
    -0.06
    POSITIVE LOGITS
     Doctors
    0.07
    провод
    0.07
     housed
    0.07
    codile
    0.07
     vehement
    0.06
     ------------------------------------------------------------------------------------------------
    0.06
    itionally
    0.06
     Bul
    0.06
     Mixer
    0.06
     Doesn
    0.06
    Act Density 0.001%

    No Known Activations