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

    Neuronpedia

    INDEX
    Explanations

    awards and critical acclaim

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     enthusiasts
    0.80
     agak
    0.75
     sad
    0.71
    acements
    0.70
     gebruik
    0.70
     ugly
    0.70
    хоро
    0.69
     interessant
    0.69
    ges
    0.69
    λοι
    0.69
    POSITIVE LOGITS
     Pulitzer
    2.01
     Grammy
    1.94
     Nobel
    1.91
     award
    1.70
     winning
    1.57
     Award
    1.56
     winner
    1.51
    Winner
    1.50
     Winner
    1.46
    Award
    1.46
    Act Density 0.130%

    No Known Activations