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

    Neuronpedia

    INDEX
    Explanations

    inform all parties

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    काब
    0.44
     seule
    0.40
    वाईसी
    0.39
    害
    0.39
    韵
    0.38
    lenie
    0.38
    olai
    0.38
     foaf
    0.38
     poes
    0.37
    ric
    0.37
    POSITIVE LOGITS
     alerts
    0.42
     Alerts
    0.41
    ǥ
    0.40
    다른
    0.38
     discoveries
    0.38
    There
    0.37
    Нет
    0.37
     खरेदी
    0.37
    код
    0.37
    డ్
    0.36
    Act Density 0.000%

    No Known Activations