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

    Neuronpedia

    INDEX
    Explanations

    Gemma team or creators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    inträ
    0.42
     上
    0.40
    察
    0.38
    বাঁ
    0.38
     POT
    0.38
    颌
    0.38
    実際
    0.37
    ):\
    0.37
     బోర్
    0.37
    juč
    0.36
    POSITIVE LOGITS
     intending
    0.46
     berharap
    0.46
    为其
    0.44
     intended
    0.44
     hopes
    0.44
     esperan
    0.44
     намере
    0.43
     hope
    0.42
    对其
    0.42
     создал
    0.41
    Act Density 0.075%

    No Known Activations