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

    Neuronpedia

    INDEX
    Explanations

    measures

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Yam
    -0.07
    Giving
    -0.07
     Yaz
    -0.07
    ماء
    -0.06
     humble
    -0.06
    mint
    -0.06
     Kylie
    -0.06
     saves
    -0.06
    嘹
    -0.06
     con
    -0.06
    POSITIVE LOGITS
     operand
    0.07
    注册
    0.07
    밟
    0.07
     "";
    0.07
     countert
    0.07
     rearr
    0.07
    enet
    0.07
     sexo
    0.07
    Carrier
    0.07
    冻结
    0.07
    Act Density 0.006%

    No Known Activations