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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    mathfrak
    1.17
    ीय
    1.07
     mathrm
    1.02
    ting
    0.99
    opp
    0.96
    ്യ
    0.94
    乾隆
    0.94
    ത്
    0.93
    리
    0.89
    ically
    0.88
    POSITIVE LOGITS
     havoc
    1.45
     flotte
    1.36
     juda
    1.34
     faptul
    1.27
     hoteles
    1.27
     bronce
    1.26
     hine
    1.25
     conscientious
    1.25
    िएगा
    1.24
     Gladiator
    1.24
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.