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

    Neuronpedia

    INDEX
    Explanations

    names followed by punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     jälkeen
    0.36
    ्रेसेस
    0.35
     of
    0.34
     Walker
    0.34
     Chengdu
    0.34
     Yunnan
    0.33
     Docker
    0.32
     Blueberry
    0.31
     AF
    0.31
     Pi
    0.31
    POSITIVE LOGITS
    ®.
    0.47
    。
    0.46
    ።
    0.45
    ։
    0.45
    .
    0.43
     և
    0.42
     ซึ่ง
    0.41
    which
    0.40
    !.
    0.40
    ۔
    0.40
    Act Density 0.314%

    No Known Activations