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

    Neuronpedia

    INDEX
    Explanations

    shopping and product descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     indignation
    0.59
     syntactic
    0.59
     inhomogeneities
    0.57
     paradig
    0.56
     innocuous
    0.56
     epistem
    0.54
     deleterious
    0.53
     fragmentary
    0.53
    ักษณะ
    0.52
     problemat
    0.52
    POSITIVE LOGITS
     &
    0.89
     |
    0.75
     Guide
    0.73
     Terbaik
    0.67
     guide
    0.65
     online
    0.64
     FAQs
    0.62
     सहित
    0.61
     UK
    0.59
     Online
    0.57
    Act Density 0.032%

    No Known Activations