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

    Neuronpedia

    INDEX
    Explanations

    paper, kertas, 紙

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    луй
    0.47
    roit
    0.39
     रिटायर
    0.39
     usern
    0.39
    oribus
    0.38
    KURZBESCHREIBUNG
    0.38
    ریف
    0.37
     શકાય
    0.37
    աղ
    0.37
    ərbay
    0.37
    POSITIVE LOGITS
     paper
    0.52
     kertas
    0.52
    紙
    0.52
     Paper
    0.49
    amp
    0.48
    纸
    0.46
    Paper
    0.45
     manual
    0.45
     handheld
    0.43
     Arag
    0.43
    Act Density 0.000%

    No Known Activations