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

    Neuronpedia

    INDEX
    Explanations

    at play or in effect

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    problems
    0.34
    َاب
    0.34
     понимать
    0.34
    ranges
    0.34
     منی
    0.34
    ρίου
    0.33
     பகுதியை
    0.33
    হইয়া
    0.33
    ത്തേക്ക്
    0.33
    𝑄
    0.33
    POSITIVE LOGITS
     play
    0.89
     sway
    0.63
     vogue
    0.63
     effect
    0.62
    play
    0.58
     motion
    0.56
     hand
    0.51
     prominence
    0.50
     swing
    0.48
     प्ले
    0.48
    Act Density 0.022%

    No Known Activations