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

    Neuronpedia

    INDEX
    Explanations

    volume license

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    </em>
    0.66
     }*/
    0.59
     화면
    0.58
    }`)
    0.57
     /*
    0.56
     设置
    0.56
    }`);
    0.56
     *}$
    0.54
    }*/
    0.54
     asyncio
    0.54
    POSITIVE LOGITS
    <h3>
    0.78
    How
    0.69
    *
    0.65
    <h2>
    0.65
    <h4>
    0.65
    Furthermore
    0.64
    <h1>
    0.63
    At
    0.62
    Upon
    0.62
    Moreover
    0.62
    Act Density 1.677%

    No Known Activations