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

    Neuronpedia

    INDEX
    Explanations

    binding

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    🤭
    -0.07
    uppe
    -0.07
     Âu
    -0.07
    还
    -0.06
    הזמנה
    -0.06
     Uri
    -0.06
    省级
    -0.06
    %\
    -0.06
     "^
    -0.06
    >"
    -0.06
    POSITIVE LOGITS
    踢
    0.07
     Suns
    0.07
    뽄
    0.07
    وض
    0.07
    铭记
    0.07
     intercept
    0.07
     wład
    0.06
    埚
    0.06
    iability
    0.06
     nhiễ
    0.06
    Act Density 0.019%

    No Known Activations