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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	description
    -0.08
    私は
    -0.07
     warning
    -0.07
     SetUp
    -0.07
    Wis
    -0.07
    }')↵
    -0.07
    .),
    -0.07
     제가
    -0.06
    ]))↵
    -0.06
    ')]↵
    -0.06
    POSITIVE LOGITS
     suốt
    0.07
    舯
    0.07
    ollipop
    0.07
    ivil
    0.07
    |string
    0.07
    𝑑
    0.07
    aviest
    0.07
     polym
    0.07
    CCCCCC
    0.07
    ampus
    0.06
    Act Density 1.311%

    No Known Activations