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

    Neuronpedia

    INDEX
    Explanations

    * ** followed by text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     حوالے
    0.41
    भग
    0.38
    டுக்க
    0.36
     principais
    0.35
     najważ
    0.35
     najwięks
    0.34
     setToDefault
    0.33
    สุด
    0.33
    acijos
    0.33
     terbesar
    0.32
    POSITIVE LOGITS
     whereas
    0.84
     Whereas
    0.84
    whereas
    0.76
    Whereas
    0.69
     hingegen
    0.65
     dagegen
    0.61
     Conversely
    0.59
     ours
    0.57
     Ours
    0.57
     sedangkan
    0.54
    Act Density 0.222%

    No Known Activations