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

    Neuronpedia

    INDEX
    Explanations

    start of quotation marks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ('
    1.12
    {'
    1.04
     (‘
    1.03
    ’).
    0.99
    […]
    0.99
    、、、
    0.99
    …).
    0.98
    ['
    0.96
    [...]
    0.96
    '])->
    0.95
    POSITIVE LOGITS
    ↵↵
    0.77
     pointed
    0.76
     point
    0.72
     points
    0.70
     Point
    0.70
     pointing
    0.68
    นด์
    0.67
     Points
    0.67
     Experts
    0.65
     Proceeds
    0.65
    Act Density 0.012%

    No Known Activations