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

    Neuronpedia

    INDEX
    Explanations

    keep/keeps

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ক্লা
    0.78
     dunno
    0.71
     ordres
    0.71
     nbfs
    0.70
     Ten
    0.69
    Ten
    0.67
     sollen
    0.66
     teria
    0.66
    oxyphenyl
    0.65
    naissance
    0.64
    POSITIVE LOGITS
     track
    1.05
     pace
    1.00
    track
    0.79
     Track
    0.75
    pace
    0.74
     alive
    0.73
     Pace
    0.72
     tracks
    0.69
     paced
    0.69
     ट्रैक
    0.68
    Act Density 0.022%

    No Known Activations