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

    Neuronpedia

    INDEX
    Explanations

    phrases following 'a', 'in', 'to'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    5
    0.56
    1
    0.55
    9
    0.53
    _
    0.51
    6
    0.48
    bs
    0.48
    7
    0.48
    se
    0.47
     epinephrine
    0.47
    r
    0.46
    POSITIVE LOGITS
     आरोपी
    0.50
    鍱
    0.49
     광고
    0.46
     채
    0.46
     onus
    0.45
     વી
    0.45
     paheli
    0.45
    鸷
    0.44
     Channel
    0.44
     गैंग
    0.44
    Act Density 0.000%

    No Known Activations