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

    Neuronpedia

    INDEX
    Explanations

    top followed by nothing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ড়িয়ে
    0.50
    ANNEL
    0.45
     listas
    0.45
    IFEST
    0.43
     বাধ
    0.41
    transferases
    0.40
     knees
    0.40
    别的
    0.40
    YO
    0.40
     ഏറ്റവും
    0.40
    POSITIVE LOGITS
     "--
    0.36
     space
    0.35
     ска
    0.35
    نیم
    0.35
    дела
    0.35
     joining
    0.34
     demonstrated
    0.33
     bar
    0.33
     "(
    0.33
     "")
    0.33
    Act Density 0.001%

    No Known Activations