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

    Neuronpedia

    INDEX
    Explanations

    Discrimination against groups

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Soup
    -0.08
    -de
    -0.07
    砆
    -0.07
    quiry
    -0.07
    GH
    -0.07
    -su
    -0.07
    isco
    -0.07
    SURE
    -0.06
    ，在
    -0.06
    蜾
    -0.06
    POSITIVE LOGITS
    brace
    0.07
    ButtonModule
    0.06
    remember
    0.06
    잃
    0.06
    使う
    0.06
     extending
    0.06
    anter
    0.06
     leash
    0.06
     //=
    0.06
     Meadows
    0.06
    Act Density 0.008%

    No Known Activations