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

    Neuronpedia

    INDEX
    Explanations

    numbered lists followed by colon

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    `,`
    0.50
    <unused42>
    0.48
     یې
    0.48
     €,
    0.47
    %、
    0.45
     $,
    0.45
    <unused51>
    0.44
    <unused24>
    0.43
    %","
    0.42
    若是
    0.40
    POSITIVE LOGITS
    </h2>
    1.16
    </h4>
    1.09
    </h3>
    1.01
    :**
    0.91
    :
    0.84
    ↵↵
    0.82
    ः
    0.80
    ):
    0.78
    </h1>
    0.78
    </b>
    0.78
    Act Density 3.319%

    No Known Activations