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

    Neuronpedia

    INDEX
    Explanations

    =>

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    是以
    -0.07
    研判
    -0.07
     ViewState
    -0.06
    实验室
    -0.06
    욯
    -0.06
     Bre
    -0.06
    (indent
    -0.06
    ሒ
    -0.06
    ッと
    -0.06
    老旧小区
    -0.06
    POSITIVE LOGITS
     "
    0.08
    Mayor
    0.07
     mystical
    0.07
     midd
    0.07
    Mich
    0.07
     fünf
    0.06
    ||||
    0.06
     applicants
    0.06
    ("
    0.06
    /public
    0.06
    Act Density 0.002%

    No Known Activations