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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    erun
    0.81
     Agra
    0.79
     Virol
    0.78
     Dubna
    0.77
    er
    0.75
     ApJ
    0.75
     Kral
    0.75
     dandruff
    0.75
     pandemics
    0.74
     halibut
    0.74
    POSITIVE LOGITS
     対
    0.79
     નહીં
    0.79
    锺
    0.77
     μια
    0.75
     少し
    0.73
     contrôle
    0.70
     schéma
    0.70
    PHIL
    0.69
     എന്നതാണ്
    0.68
     ડ
    0.68
    Act Density 0.000%

    No Known Activations