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

    Neuronpedia

    INDEX
    Explanations

    call to action

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hues
    1.23
    ↵
    1.13
     ture
    1.09
     quirks
    1.03
     cultures
    1.02
     fielding
    1.02
     follicles
    1.01
    '
    1.01
     innings
    1.00
     inks
    1.00
    POSITIVE LOGITS
    ”).
    1.04
    lian
    0.96
    owymi
    0.95
    )”.
    0.95
    syscall
    0.95
    ).[
    0.94
    apadani
    0.91
    ).”
    0.91
    lardan
    0.90
    сцю
    0.90
    Act Density 0.111%

    No Known Activations