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

    Neuronpedia

    INDEX
    Explanations

    head >

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Pertama
    0.67
     G
    0.65
     أب
    0.64
    ⁸
    0.63
    ablo
    0.61
    ℝ
    0.61
    ων
    0.61
    ര
    0.61
    ig
    0.60
     Method
    0.59
    POSITIVE LOGITS
    </tr>
    0.79
    </ul>
    0.79
    ↵
    0.75
    <tr>
    0.71
    सभी
    0.71
    </li>
    0.70
    Cidade
    0.70
    ></
    0.68
     hemen
    0.65
    plugins
    0.64
    Act Density 0.002%

    No Known Activations