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

    Neuronpedia

    INDEX
    Explanations

    overall tone

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     নূতন
    0.41
     ethnicities
    0.40
    相当于
    0.40
     വീ
    0.40
     tect
    0.38
     resemble
    0.38
     dè
    0.38
     resembled
    0.37
    ulence
    0.37
     resembles
    0.37
    POSITIVE LOGITS
     overall
    0.73
    overall
    0.72
    整體
    0.72
     insgesamt
    0.71
    整体
    0.68
     Gesamt
    0.66
     broader
    0.64
    Overall
    0.63
     Insgesamt
    0.62
    总体
    0.61
    Act Density 0.448%

    No Known Activations