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

    Neuronpedia

    INDEX
    Explanations

    lists with explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ...).
    0.45
    %).
    0.40
    …).
    0.36
    }\}$.
    0.35
    ])$.
    0.35
    ]$.
    0.34
     "").
    0.33
    !).
    0.32
    ...),
    0.31
     n
    0.31
    POSITIVE LOGITS
    ↵↵
    0.73
    ：
    0.67
    ः
    0.65
    </h4>
    0.64
    ↵
    0.64
    </h2>
    0.62
    ׃
    0.62
     interstitiis
    0.61
     (+
    0.61
    :**
    0.59
    Act Density 8.314%

    No Known Activations