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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    s
    1.03
    الم
    0.82
    ्स
    0.79
    ان
    0.78
    曹
    0.77
    আমরা
    0.77
    ों
    0.76
    ول
    0.76
    ک
    0.76
    অ্যাপ
    0.73
    POSITIVE LOGITS
    𝑭
    0.84
     oppressed
    0.84
    hened
    0.81
     fiss
    0.81
     dessert
    0.80
     diamond
    0.79
     renta
    0.79
     imposing
    0.78
     aspect
    0.76
     lumi
    0.76
    Act Density 0.009%

    No Known Activations