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

    Neuronpedia

    INDEX
    Explanations

    list concatenation, code, Japanese

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    NASDAQ
    0.49
    ٣
    0.47
     这里
    0.47
     করিতাম
    0.47
     siden
    0.45
    Merhaba
    0.45
     Baroque
    0.44
     mutta
    0.44
    ۳
    0.44
     Criteria
    0.43
    POSITIVE LOGITS
    lab
    0.49
    rase
    0.48
    l
    0.46
    t
    0.45
    人數
    0.45
     принадле
    0.45
    subsec
    0.45
    li
    0.44
    llo
    0.43
    lains
    0.43
    Act Density 0.001%

    No Known Activations