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

    Neuronpedia

    INDEX
    Explanations

    singular and fractional quantities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ecosystems
    0.48
    platforms
    0.47
     フレ
    0.46
     именно
    0.46
     platforms
    0.45
     inequalities
    0.45
     ninety
    0.45
    ports
    0.45
     imaginations
    0.45
     imagin
    0.45
    POSITIVE LOGITS
     einzige
    0.64
     buah
    0.59
     маленький
    0.58
    టో
    0.57
     छोटा
    0.56
     ጥላ
    0.56
    THING
    0.55
     affair
    0.55
     चीज
    0.55
     enkele
    0.55
    Act Density 0.218%

    No Known Activations