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

    Neuronpedia

    INDEX
    Explanations

    concepts and methods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Delivery
    0.49
     Image
    0.47
     Animation
    0.46
     Camera
    0.46
     Day
    0.45
     Awake
    0.45
    再次
    0.44
     Milli
    0.43
     Gate
    0.43
     Salon
    0.43
    POSITIVE LOGITS
     কিংবা
    0.56
     principalmente
    0.55
     aŭ
    0.50
     주로
    0.50
    を使って
    0.49
     mainly
    0.49
     alebo
    0.49
     distaste
    0.49
     või
    0.49
     hauptsächlich
    0.49
    Act Density 0.022%

    No Known Activations