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

    Neuronpedia

    INDEX
    Explanations

    50%

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    184
    -0.08
    ighbors
    -0.08
    Dou
    -0.08
    wart
    -0.08
    ستم
    -0.08
    546
    -0.07
     wished
    -0.07
    ighbor
    -0.07
    oint
    -0.07
    رح
    -0.07
    POSITIVE LOGITS
    比例
    0.14
     percentages
    0.13
     percentage
    0.12
    percentage
    0.12
     Percentage
    0.12
     ശതമ
    0.12
    _percentage
    0.12
     प्रतिशत
    0.12
    Percentage
    0.12
     proportions
    0.12
    Act Density 0.043%

    No Known Activations