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

    Neuronpedia

    INDEX
    Explanations

    *

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ();}
    1.10
    </td>
    1.10
    ()}
    1.07
    </h1>
    1.02
    <i>
    0.99
    []}
    0.99
    ";}
    0.94
     Архивная
    0.93
    </h2>
    0.90
    </b>
    0.90
    POSITIVE LOGITS
     **
    4.27
    **
    3.18
     **,
    2.46
    <strong>
    2.35
     (**
    2.31
    <b>
    2.30
     **/
    2.13
     ***
    2.12
     "**
    2.12
    **.
    2.08
    Act Density 5.342%

    No Known Activations