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

    Neuronpedia

    INDEX
    Explanations

    end of sentence or phrase

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     intricacies
    0.44
     intric
    0.40
     objets
    0.36
     سامنے
    0.35
     물론
    0.35
     autre
    0.34
    年在
    0.33
     সাধারণ
    0.33
     fabricación
    0.32
    ॒
    0.32
    POSITIVE LOGITS
    </b>
    0.86
    </u>
    0.85
    </strong>
    0.61
    」
    0.61
    </code>
    0.60
    ‬
    0.54
    』
    0.54
    》
    0.53
    </a>
    0.52
    </i>
    0.52
    Act Density 0.871%

    No Known Activations