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

    Neuronpedia

    INDEX
    Explanations

    product names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     esta
    0.57
     sloop
    0.57
     Và
    0.56
     fury
    0.56
     Questa
    0.55
     mower
    0.55
    스럽
    0.55
     hacer
    0.54
     questa
    0.54
     Fury
    0.54
    POSITIVE LOGITS
    ücksicht
    0.46
    ோடு
    0.43
    regions
    0.43
    müş
    0.42
    примеча
    0.42
     সেজন্য
    0.42
    군
    0.41
     литера
    0.41
     নিয়ন্ত্রণে
    0.41
    חים
    0.40
    Act Density 0.000%

    No Known Activations