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

    Neuronpedia

    INDEX
    Explanations

    make a difference

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AND
    0.52
     and
    0.47
    X
    0.46
    and
    0.45
     своих
    0.45
     making
    0.43
     Deine
    0.41
     NSF
    0.41
     Decision
    0.40
     AGAIN
    0.40
    POSITIVE LOGITS
     difference
    0.62
     diferença
    0.61
    difference
    0.60
     sense
    0.56
     diferencia
    0.55
     perbedaan
    0.55
     differenza
    0.54
     البعض
    0.52
     फरक
    0.52
     verschil
    0.52
    Act Density 0.013%

    No Known Activations