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

    Neuronpedia

    INDEX
    Explanations

    single digit numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    愛情
    -0.08
     motivo
    -0.07
    RID
    -0.07
     dov
    -0.06
    وار
    -0.06
     Она
    -0.06
    玱
    -0.06
    성이
    -0.06
    @Service
    -0.06
     yielding
    -0.06
    POSITIVE LOGITS
     Başkanlığı
    0.08
     Năm
    0.08
    _words
    0.08
     xls
    0.07
    Bracket
    0.07
    😆
    0.07
    八字
    0.07
    xC
    0.07
     WEEK
    0.07
    艾滋
    0.07
    Act Density 0.001%

    No Known Activations