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

    Neuronpedia

    INDEX
    Explanations

    Reports, revisions, and details

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    MAIN
    -0.06
    茶
    -0.06
    Thông
    -0.06
    WEST
    -0.06
    자를
    -0.05
    uber
    -0.05
    '",↵
    -0.05
     Finnish
    -0.05
    delivr
    -0.05
    ектор
    -0.05
    POSITIVE LOGITS
    .cs
    0.07
     京
    0.07
    ंव
    0.07
     розп
    0.07
    _PRIVATE
    0.07
    _suspend
    0.06
     Bergen
    0.06
     kapı
    0.06
     매매
    0.06
    _TEST
    0.06
    Act Density 0.810%

    No Known Activations