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

    Neuronpedia

    INDEX
    Explanations

    examples and definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    гти
    0.39
     فاط
    0.38
    ﻊ
    0.38
    टने
    0.38
    vvvert
    0.37
    叁章
    0.37
    гля
    0.36
    زام
    0.36
     adquis
    0.36
    要知道
    0.36
    POSITIVE LOGITS
    </i>
    0.45
    出
    0.44
     */
    0.42
     consume
    0.41
    */
    0.40
    </li>
    0.38
    </sup>
    0.38
     있었
    0.37
    提出
    0.37
    mp
    0.37
    Act Density 0.000%

    No Known Activations