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

    Neuronpedia

    INDEX
    Explanations

    utf

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     October
    -0.07
     Institutional
    -0.07
     June
    -0.06
     -*
    -0.06
     Kot
    -0.06
    ensored
    -0.06
    聚
    -0.06
    ön
    -0.06
     Jam
    -0.06
    uted
    -0.06
    POSITIVE LOGITS
    یک
    0.07
    .transport
    0.06
    ाहक
    0.06
    .waitKey
    0.06
     disparity
    0.06
    Denied
    0.06
     kadınlar
    0.06
     borrowers
    0.06
     Ли
    0.06
    CKET
    0.06
    Act Density 0.000%

    No Known Activations