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

    Neuronpedia

    INDEX
    Explanations

    pronoun followed by action verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     हाद
    0.69
    cand
    0.69
    忐
    0.66
     milij
    0.66
     besø
    0.66
    敏感
    0.66
     malaise
    0.66
    葺
    0.64
     honeymoon
    0.64
    快適
    0.64
    POSITIVE LOGITS
     lung
    1.33
     roared
    1.16
     unleashing
    1.08
     roar
    1.02
     hurled
    1.00
     screamed
    1.00
    Lung
    0.96
     roaring
    0.96
     shouted
    0.96
     snar
    0.95
    Act Density 0.132%

    No Known Activations