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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     reinst
    0.82
    ientos
    0.79
    Š
    0.79
    ುಂಬ
    0.77
    ্ধ্য
    0.76
    ãs
    0.75
    Съ
    0.75
    ்கள்
    0.74
     eficiência
    0.74
    Aus
    0.73
    POSITIVE LOGITS
     bulunan
    0.84
     En
    0.81
     El
    0.75
    ח
    0.71
     bypass
    0.68
    hile
    0.68
     বলিলাম
    0.68
     sign
    0.67
     Le
    0.66
    pliance
    0.65
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.