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

    Neuronpedia

    INDEX
    Explanations

    consequence or comparison

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     và
    0.63
     και
    0.58
     और
    0.57
     و
    0.55
     и
    0.54
     மற்றும்
    0.51
    และ
    0.51
     and
    0.50
     અને
    0.49
     এবং
    0.49
    POSITIVE LOGITS
     вследствие
    0.42
    逐渐
    0.38
     მათი
    0.37
    傾向
    0.36
    लोनी
    0.36
     совокуп
    0.36
    enstein
    0.36
     inescap
    0.36
     insgesamt
    0.35
     posthum
    0.35
    Act Density 0.042%

    No Known Activations