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

    Neuronpedia

    INDEX
    Explanations

    studies indicate significant findings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Hopefully
    0.50
    Hopefully
    0.43
     Presumably
    0.42
     diharapkan
    0.42
     dikatakan
    0.41
     presumably
    0.40
    جست
    0.39
    Dollars
    0.39
     Someone
    0.38
    Someone
    0.38
    POSITIVE LOGITS
     significant
    1.14
     considerable
    0.90
    significant
    0.89
     substantial
    0.84
     significativas
    0.84
     significativa
    0.83
     significative
    0.82
    Significant
    0.80
     significativo
    0.79
     Significant
    0.78
    Act Density 0.012%

    No Known Activations