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

    Neuronpedia

    INDEX
    Explanations

    specific descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    seiten
    0.52
    مدة
    0.46
    ში
    0.44
     Sonnen
    0.43
    䐍
    0.43
     Moser
    0.43
    㹂
    0.43
     adhesives
    0.41
    ッシング
    0.40
    directional
    0.40
    POSITIVE LOGITS
    мий
    0.47
     unknow
    0.43
    都是
    0.43
     entspre
    0.43
    </li>
    0.42
    等於
    0.42
    YS
    0.42
    </td>
    0.41
    वाइड
    0.41
    eterminate
    0.41
    Act Density 0.003%

    No Known Activations