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

    Neuronpedia

    INDEX
    Explanations

    importing libraries and data structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ).}
    0.59
    )。
    0.58
    ).\\
    0.55
    Grunge
    0.54
    (“
    0.54
    \%),
    0.54
     )।
    0.52
    ’),
    0.52
    ).</
    0.52
    )،
    0.50
    POSITIVE LOGITS
     "";
    1.11
     [];
    1.07
     {};
    1.01
     '';
    0.95
     {}
    0.86
     []
    0.83
     null
    0.74
     ""
    0.74
     None
    0.73
    [];
    0.66
    Act Density 0.156%

    No Known Activations