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

    Neuronpedia

    INDEX
    Explanations

    exception resolution tried

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ,…
    1.08
    …,
    1.06
    .…
    1.04
    )…
    1.04
     …
    0.97
     …,
    0.92
     „
    0.92
    •
    0.91
    ‘’
    0.91
    <unused2174>
    0.90
    POSITIVE LOGITS
    3.44
    3.17
    2.85
    2.62
    2.40
    2.34
    2.22
    2.05
    2.03
    1.98
    Act Density 0.156%

    No Known Activations