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

    Neuronpedia

    INDEX
    Explanations

    impression

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sure
    0.93
     SURE
    0.75
    삶
    0.74
    }|^
    0.72
    yn
    0.72
    amt
    0.71
    ง่าย
    0.70
    amore
    0.69
     textAlign
    0.68
    gm
    0.68
    POSITIVE LOGITS
     impression
    2.21
    impression
    1.90
     impressions
    1.81
     Impression
    1.81
     impressão
    1.62
     Eindruck
    1.49
     impresión
    1.48
     Impressions
    1.47
    Impress
    1.30
     впечатление
    1.21
    Act Density 0.060%

    No Known Activations