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

    Neuronpedia

    INDEX
    Explanations

    using/use

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Mari
    -0.07
     Ky
    -0.07
    serious
    -0.07
     Ster
    -0.06
     Cant
    -0.06
    UnitTest
    -0.06
    	F
    -0.06
    _Normal
    -0.06
    _I
    -0.06
    She
    -0.06
    POSITIVE LOGITS
    ief
    0.07
    AGER
    0.06
    ери
    0.06
     ảnh
    0.06
    clamation
    0.06
    оген
    0.06
    レス
    0.06
    -ajax
    0.06
    ẫ
    0.06
    ريط
    0.06
    Act Density 0.032%

    No Known Activations