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

    Neuronpedia

    INDEX
    Explanations

    mining and academic papers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ladr
    0.44
     baryon
    0.43
    rikes
    0.43
     biota
    0.43
    ട്ടില്ല
    0.42
     basalt
    0.42
     renewables
    0.41
     holdings
    0.40
     strontium
    0.40
     almacen
    0.40
    POSITIVE LOGITS
     Paper
    0.55
    Paper
    0.54
     paper
    0.48
    紙
    0.46
     पेपर
    0.45
     紙
    0.44
     Papers
    0.43
     бума
    0.43
     کاغذ
    0.43
     kertas
    0.43
    Act Density 0.005%

    No Known Activations