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

    Neuronpedia

    INDEX
    Explanations

    calculating monetary returns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    そもそも
    0.45
    StudentRecord
    0.44
    probabilities
    0.43
     সংখ্য
    0.42
    嗇
    0.42
    AgentError
    0.40
     নেন
    0.40
    ẵn
    0.40
     coeff
    0.40
     இருப்பதால்
    0.40
    POSITIVE LOGITS
     expand
    0.48
     increase
    0.46
     approximately
    0.45
     transformed
    0.45
     baada
    0.44
     transform
    0.42
     aumento
    0.41
     doubled
    0.41
     después
    0.41
     превра
    0.40
    Act Density 0.012%

    No Known Activations