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

    Neuronpedia

    INDEX
    Explanations

    listing or continuing points

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵↵
    0.37
     διαδικ
    0.35
    ↵
    0.32
    нер
    0.32
    :-)
    0.31
    很多
    0.31
    嘻
    0.30
    ওয়ান
    0.30
    (){}
    0.30
    ＂
    0.30
    POSITIVE LOGITS
     Además
    0.48
     Furthermore
    0.46
     மொத்தம்
    0.46
    ):
    0.44
     તેમજ
    0.43
     તથા
    0.43
    }}:
    0.42
    *:
    0.41
    »:
    0.41
     sekä
    0.40
    Act Density 0.027%

    No Known Activations