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

    Neuronpedia

    INDEX
    Explanations

    layout/rendering issues

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ococci
    0.41
    。[
    0.37
     =[
    0.37
    }[
    0.36
    ),]$
    0.36
     Whereas
    0.36
    に対する
    0.36
    Conversely
    0.35
     இனி
    0.35
    PARTMENT
    0.34
    POSITIVE LOGITS
     lest
    0.94
    以免
    0.94
     because
    0.94
     gdyż
    0.89
     deoarece
    0.88
     γιατί
    0.87
     کیونکہ
    0.86
     কেননা
    0.86
     ஏனெனில்
    0.83
     eftersom
    0.82
    Act Density 0.000%

    No Known Activations