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

    Neuronpedia

    INDEX
    Explanations

    )

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    akah
    -0.06
     taş
    -0.06
     Zag
    -0.06
     kinh
    -0.06
     امن
    -0.06
     şart
    -0.06
    267
    -0.06
    .Designer
    -0.06
     interchangeable
    -0.06
    Accent
    -0.06
    POSITIVE LOGITS
    ｲ
    0.07
     BUT
    0.07
    _enter
    0.07
     Rail
    0.07
    0.07
     contain
    0.07
    طب
    0.06
     lawyers
    0.06
     معلومات
    0.06
     Labour
    0.06
    Act Density 0.004%

    No Known Activations