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

    Neuronpedia

    INDEX
    Explanations

    polyamory

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     BMW
    -0.08
    Uno
    -0.07
    监管
    -0.07
    借
    -0.06
     niños
    -0.06
    fuck
    -0.06
    �
    -0.06
    uish
    -0.06
     Garc
    -0.06
    adan
    -0.06
    POSITIVE LOGITS
    DidAppear
    0.07
     "=",
    0.07
    حكيم
    0.07
    みると
    0.07
    }?
    0.06
     Söz
    0.06
    而后
    0.06
     talks
    0.06
    铴
    0.06
    \models
    0.06
    Act Density 0.014%

    No Known Activations