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

    Neuronpedia

    INDEX
    Explanations

    code, conditions, or definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    **:
    1.12
     (**
    1.10
    اہم
    1.05
     LOTRAchievement
    1.04
    **,
    1.02
    ***",
    1.00
    ****",
    0.99
     acompa
    0.98
     필요
    0.98
    ເລັກ
    0.97
    POSITIVE LOGITS
    .
    0.95
    )
    0.80
     )
    0.80
    s
    0.75
    ।
    0.75
    l
    0.74
    ?
    0.74
    ]
    0.69
    u
    0.69
    f
    0.68
    Act Density 1.530%

    No Known Activations