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

    Neuronpedia

    INDEX
    Explanations

    laziness and boredom

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    able
    0.71
     W
    0.67
    8
    0.63
     V
    0.62
     n
    0.60
     kamera
    0.60
    4
    0.60
    (
    0.59
    it
    0.59
     metri
    0.57
    POSITIVE LOGITS
     laziness
    0.93
     sluggish
    0.80
     monotonous
    0.75
     monotony
    0.74
     lackluster
    0.73
     apathy
    0.72
    laz
    0.71
    惰
    0.71
     leth
    0.71
     malaise
    0.70
    Act Density 0.085%

    No Known Activations