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

    Neuronpedia

    INDEX
    Explanations

    winning championships and titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     interfacing
    0.58
     উপাদান
    0.57
     sorption
    0.57
    ποιη
    0.57
     adsorption
    0.57
     perceptible
    0.57
     ওষুধের
    0.55
     inkjet
    0.55
     ఉత్ప
    0.54
     camphor
    0.54
    POSITIVE LOGITS
     victories
    1.02
    🏆
    0.95
     victorious
    0.91
     championships
    0.91
     championship
    0.90
     winning
    0.89
     remporte
    0.87
    years
    0.86
     years
    0.86
     trophies
    0.85
    Act Density 0.091%

    No Known Activations