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

    Neuronpedia

    INDEX
    Explanations

    exceeded expectations, won

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     usefulness
    0.34
     동작
    0.34
     chromatography
    0.33
     Dressing
    0.33
     నో
    0.33
     cryptographic
    0.33
     usability
    0.32
     Watering
    0.32
     playroom
    0.32
     tortilla
    0.32
    POSITIVE LOGITS
     dominate
    0.69
     dominates
    0.58
     dominated
    0.50
     dominating
    0.49
     scored
    0.49
     overcame
    0.48
     narrowly
    0.48
    拿下
    0.48
     topped
    0.47
     garnered
    0.46
    Act Density 0.008%

    No Known Activations