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

    Neuronpedia

    INDEX
    Explanations

    micro

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    と思
    -0.07
     Initially
    -0.07
    -neutral
    -0.07
    博士
    -0.06
    Kh
    -0.06
    net
    -0.06
    ถ
    -0.06
    床
    -0.06
     DIG
    -0.06
    KHR
    -0.06
    POSITIVE LOGITS
    IBOutlet
    0.06
    .flink
    0.06
    .Future
    0.06
    outines
    0.06
     Pharma
    0.06
    #----------------------------------------------------------------------------
    0.05
     Střed
    0.05
    ]=]
    0.05
    PWD
    0.05
    訴
    0.05
    Act Density 0.014%

    No Known Activations