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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    hwar
    1.08
     основ
    1.07
     attitudes
    0.97
    帏
    0.96
    ಾಗಿ
    0.95
    ្រ
    0.94
    es
    0.94
    خ
    0.93
    प्लीट
    0.93
     Heraus
    0.92
    POSITIVE LOGITS
     значит
    1.31
     balsamic
    1.26
     cuenta
    1.23
    1.22
     silver
    1.20
    तात
    1.20
    Cuenta
    1.18
    1.18
    Exception
    1.18
     contaba
    1.17
    Act Density 0.000%

    No Known Activations