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

    Neuronpedia

    INDEX
    Explanations

    certainty

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ব্যক্ত
    0.37
    assel
    0.37
     away
    0.36
    𒌓
    0.36
    }());
    0.36
     signing
    0.36
     Lod
    0.36
     Nai
    0.36
    互動
    0.36
     abutting
    0.36
    POSITIVE LOGITS
    Neder
    0.38
     Welcome
    0.36
    welcome
    0.36
     welcome
    0.35
     facilité
    0.35
     conclusions
    0.34
     Bound
    0.34
     SOCIAL
    0.33
    पणा
    0.33
    Welcome
    0.33
    Act Density 0.000%

    No Known Activations