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

    Neuronpedia

    INDEX
    Explanations

    ai can do

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    म
    0.51
    Information
    0.47
    ற்ப
    0.45
     Speaker
    0.45
     मानवता
    0.44
    商品を
    0.44
     Scalar
    0.44
     Eyre
    0.43
    常に
    0.42
     уточ
    0.42
    POSITIVE LOGITS
    洼
    0.46
     margarine
    0.42
    MathMarks
    0.41
     Cessna
    0.41
    仆
    0.41
     和
    0.40
    ოლოგი
    0.40
    以上の
    0.39
     líquidos
    0.39
    renamiento
    0.39
    Act Density 0.002%

    No Known Activations