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

    Neuronpedia

    INDEX
    Explanations

    blog post request

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    探讨
    0.50
    TREND
    0.49
     compreender
    0.48
     encompasses
    0.46
    정책
    0.46
    ध्य
    0.46
     문제를
    0.46
     envis
    0.46
     분석
    0.45
    례
    0.44
    POSITIVE LOGITS
     Depois
    0.54
     पत्नी
    0.52
     Dopo
    0.50
     dopo
    0.50
     moglie
    0.50
     dumplings
    0.49
     appartement
    0.49
     avaient
    0.49
     apartamento
    0.49
     deux
    0.48
    Act Density 0.017%

    No Known Activations