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
    言って
    -0.07
     склад
    -0.07
    Fin
    -0.07
    .AddRange
    -0.07
     собою
    -0.06
     nhé
    -0.06
     tabs
    -0.06
     Han
    -0.06
    獲得
    -0.06
    Leg
    -0.06
    POSITIVE LOGITS
    θηκε
    0.06
    ुजर
    0.06
    ीश
    0.06
    भ
    0.06
     Abdel
    0.06
    оба
    0.06
     Kirk
    0.06
     Wireless
    0.06
    dık
    0.06
    ्रभ
    0.06
    Act Density 0.010%

    No Known Activations