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

    Neuronpedia

    INDEX
    Explanations

    why np

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    i
    0.61
    >";
    0.47
    ي
    0.47
    a
    0.46
     satış
    0.46
    rate
    0.45
     répart
    0.45
    service
    0.45
     ventes
    0.45
    }";
    0.44
    POSITIVE LOGITS
    ṇ
    0.39
     Hoyt
    0.39
    簡単な
    0.38
    ிய
    0.38
     Blynk
    0.38
    ум
    0.37
    援助
    0.37
    骨
    0.37
    ђ
    0.37
     hoe
    0.37
    Act Density 0.000%

    No Known Activations