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

    Neuronpedia

    INDEX
    Explanations

    etcetera, conjunctions, and lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    =
    0.52
    also
    0.48
    Also
    0.44
    of
    0.44
    2
    0.43
    with
    0.41
     also
    0.40
     که
    0.39
     from
    0.39
     якого
    0.39
    POSITIVE LOGITS
     etc
    0.64
     போன்றவை
    0.63
    などを
    0.62
    等方面
    0.62
    などが
    0.61
     тощо
    0.61
     इत्यादी
    0.61
     etcétera
    0.61
     ইত্যাদি
    0.60
    等を
    0.59
    Act Density 0.000%

    No Known Activations