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

    Neuronpedia

    INDEX
    Explanations

    seeing outcomes and states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     gevoel
    0.55
     Feeling
    0.53
    feeling
    0.53
     observed
    0.50
     чувство
    0.50
    Feeling
    0.50
     feelings
    0.49
    Experiences
    0.48
     feeling
    0.48
     suara
    0.47
    POSITIVE LOGITS
     firsthand
    0.70
     progression
    0.64
     reflection
    0.63
     glimmer
    0.63
     difference
    0.62
     fruits
    0.59
     প্রতিফলন
    0.59
     झलक
    0.56
     carnage
    0.56
     devastation
    0.55
    Act Density 0.017%

    No Known Activations