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

    Neuronpedia

    INDEX
    Explanations

    class

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    uitive
    -0.08
    פופולרי
    -0.07
    횟
    -0.07
     Charlottesville
    -0.07
     overposting
    -0.07
    指令
    -0.07
    ε
    -0.06
    士兵
    -0.06
    .StoredProcedure
    -0.06
    شرف
    -0.06
    POSITIVE LOGITS
    助力
    0.07
    咱
    0.07
    _RF
    0.07
    engkap
    0.07
     trends
    0.07
    feb
    0.07
    imity
    0.07
    .=
    0.07
     mężczyzn
    0.07
    _Real
    0.07
    Act Density 0.082%

    No Known Activations