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

    Neuronpedia

    INDEX
    Explanations

    versus and vs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ᒐ
    0.43
     основним
    0.43
    ించారు
    0.42
    ！！
    0.41
     보면은
    0.41
    最低
    0.41
     โดย
    0.41
     éventuellement
    0.41
    𝑛
    0.40
    就被
    0.39
    POSITIVE LOGITS
     vs
    0.75
     versus
    0.75
     and
    0.66
     Vs
    0.58
     и
    0.57
     Versus
    0.57
     VS
    0.56
    ’
    0.54
     आणि
    0.52
     Revisited
    0.52
    Act Density 0.061%

    No Known Activations