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

    Neuronpedia

    INDEX
    Explanations

    of, in, or from

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    xbc
    -0.07
    ,retain
    -0.07
    .One
    -0.06
     Wanna
    -0.06
    场上
    -0.06
    삔
    -0.06
    央行
    -0.06
    athon
    -0.06
     Jamaica
    -0.06
    ايا
    -0.06
    POSITIVE LOGITS
     legend
    0.08
     Potential
    0.07
     fibers
    0.07
     residues
    0.07
    可靠
    0.07
    缺陷
    0.07
     for
    0.07
     Unsupported
    0.07
    �
    0.07
     EZ
    0.07
    Act Density 0.471%

    No Known Activations