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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    𝟑
    2.19
    𝒎
    2.05
    𝟰
    1.92
    د
    1.90
     illusions
    1.89
    enay
    1.86
    𝒑
    1.84
     speculation
    1.82
    𝑑
    1.82
    𝒌
    1.81
    POSITIVE LOGITS
    ly
    1.90
    subdir
    1.76
    Ig
    1.74
    밥
    1.72
    দ্বার
    1.72
    ни
    1.69
    ary
    1.67
    Quién
    1.67
    press
    1.66
    и
    1.66
    Act Density 0.002%

    No Known Activations