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

    Neuronpedia

    INDEX
    Explanations

    Code/Error messages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     healthcare
    -0.07
    čast
    -0.07
     meisjes
    -0.06
    /trans
    -0.06
     defect
    -0.06
     아닌
    -0.06
    anted
    -0.06
     suit
    -0.06
    igr
    -0.06
     boiled
    -0.06
    POSITIVE LOGITS
    /styles
    0.07
     muschi
    0.06
     пон
    0.06
    ์ใน
    0.06
    оні
    0.06
     Jahr
    0.06
     уд
    0.06
     vào
    0.06
     Namen
    0.06
     stylist
    0.06
    Act Density 0.033%

    No Known Activations