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

    Neuronpedia

    INDEX
    Explanations

    respectively or and

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ,
    1.14
    ،
    0.75
    ),
    0.70
    -
    0.66
    :
    0.64
    ...
    0.61
    #,
    0.61
    --
    0.59
    )
    0.58
    、
    0.56
    POSITIVE LOGITS
     odnosno
    1.12
     czyli
    1.06
     illetve
    0.96
     yani
    0.96
     valamint
    0.95
     vilket
    0.93
     ovvero
    0.92
     albeit
    0.92
     która
    0.89
     incluindo
    0.88
    Act Density 1.161%

    No Known Activations