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

    Neuronpedia

    INDEX
    Explanations

    even, also

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dieser
    0.50
     dieses
    0.43
     diminishes
    0.42
     questa
    0.41
     usually
    0.41
     corresponds
    0.40
     această
    0.40
     này
    0.40
     this
    0.38
     differs
    0.38
    POSITIVE LOGITS
     همچنین
    0.55
     Также
    0.52
    我们也
    0.51
     таксама
    0.51
     Bahkan
    0.50
     גם
    0.49
     també
    0.49
     также
    0.48
     також
    0.48
     hatta
    0.47
    Act Density 0.134%

    No Known Activations