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

    Neuronpedia

    INDEX
    Explanations

    hierarchies, values, comics, aircraft

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hous
    0.44
    洗濯
    0.43
    াদা
    0.42
    农
    0.41
    집
    0.41
    湖
    0.41
    ্ৰ
    0.40
    łą
    0.40
    师
    0.40
     uppermost
    0.40
    POSITIVE LOGITS
     វា
    0.52
     IF
    0.48
     букмекер
    0.48
     önemlidir
    0.47
     Überblick
    0.46
     Fahrzeuge
    0.46
    ík
    0.44
     Beige
    0.44
    icama
    0.44
     দ্য
    0.43
    Act Density 0.001%

    No Known Activations