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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    s
    1.26
     l
    1.16
     r
    1.04
     d
    0.92
     /
    0.92
     detailing
    0.89
     Shri
    0.88
     Krankenhaus
    0.87
    其他
    0.86
     interessante
    0.86
    POSITIVE LOGITS
    сі
    1.13
    espèces
    1.05
    とき
    1.02
    Ін
    1.02
    ಲ್ಲು
    1.01
    𝘔
    1.01
    𝔪
    0.98
    rai
    0.96
     dentées
    0.92
    ліза
    0.91
    Act Density 0.107%

    No Known Activations