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

    Neuronpedia

    INDEX
    Explanations

    its core, purpose, or characteristics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    他们的
    0.52
    Their
    0.45
     leurs
    0.44
    their
    0.42
     Their
    0.41
     അവരുടെ
    0.41
    他們的
    0.41
    তাদের
    0.41
     their
    0.40
     jejich
    0.40
    POSITIVE LOGITS
     inhabitants
    0.62
     predecessor
    0.59
     contents
    0.57
     existence
    0.55
     entirety
    0.55
     occupants
    0.50
     inception
    0.49
     abitanti
    0.48
     origins
    0.48
     own
    0.47
    Act Density 0.202%

    No Known Activations