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

    Neuronpedia

    INDEX
    Explanations

    "was" followed by verbs of thought or feeling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     protective
    0.42
    الة
    0.39
     inhomogeneity
    0.39
     পাচ্ছেন
    0.39
     inhomogeneous
    0.39
     heterogeneity
    0.38
    ా
    0.38
     cout
    0.38
     tokom
    0.38
     जाना
    0.37
    POSITIVE LOGITS
     wondering
    0.54
     Hoping
    0.54
     hoping
    0.53
     thinking
    0.49
    thinking
    0.47
     tempted
    0.45
     researching
    0.45
     browsing
    0.43
     bullied
    0.43
     misled
    0.42
    Act Density 0.006%

    No Known Activations