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

    Neuronpedia

    INDEX
    Explanations

    think step by step

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     engagement
    0.75
     engagements
    0.73
    FUL
    0.73
     Engagement
    0.69
    aments
    0.68
     rallied
    0.67
     gatherings
    0.67
     Packed
    0.67
    packed
    0.66
     arrangements
    0.66
    POSITIVE LOGITS
     slowly
    1.14
     continuously
    1.05
     quietly
    1.02
     silently
    0.95
     gently
    0.94
     lentamente
    0.92
     softly
    0.91
     step
    0.89
     peacefully
    0.89
     smoothly
    0.89
    Act Density 0.035%

    No Known Activations