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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     করা
    1.05
     adding
    1.00
    തെന്നും
    0.97
     perceiving
    0.92
    രിക്കുന്നത്
    0.90
     слова
    0.85
     putting
    0.84
    ल्यावर
    0.84
    angering
    0.83
     বলা
    0.83
    POSITIVE LOGITS
     came
    2.02
     went
    1.97
     took
    1.91
     underwent
    1.82
     deserves
    1.80
     became
    1.77
     grew
    1.75
     represents
    1.73
     belongs
    1.67
     began
    1.66
    Act Density 0.486%

    No Known Activations