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

    Neuronpedia

    INDEX
    Explanations

    predicting text structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    il
    0.53
    DOM
    0.50
    ie
    0.47
    FileNotFound
    0.47
    Model
    0.46
    Coord
    0.46
     file
    0.46
     DOM
    0.45
    Evaluation
    0.45
    User
    0.45
    POSITIVE LOGITS
    kenalkan
    0.49
    шли
    0.48
     और
    0.48
    andaag
    0.47
    రించి
    0.46
     endorsements
    0.45
     Surgeons
    0.45
     rescheduled
    0.44
    anyakan
    0.43
    бами
    0.43
    Act Density 0.008%

    No Known Activations