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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    èł¹
    -0.27
    ExecutionContext
    -0.26
    AccessException
    -0.26
    æĦŁæĥħ
    -0.26
    çĽĤ
    -0.26
     Romance
    -0.25
    ç½ijç«Ļé¦ĸ页
    -0.24
     ÑģоÑģ
    -0.24
    -article
    -0.24
    vice
    -0.24
    POSITIVE LOGITS
    第ä¸īæĸ¹
    0.31
     lett
    0.28
    __',
    0.27
    æĭħä¿Ŀ
    0.26
    ivor
    0.25
    ĸ
    0.25
     bringing
    0.24
    ering
    0.24
    dea
    0.24
    è·µ
    0.24
    Act Density 0.919%

    No Known Activations