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

    Neuronpedia

    INDEX
    Explanations

    especially

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    :
    0.44
    ogh
    0.42
    ue
    0.41
    sort
    0.39
     クリーム
    0.38
     creamy
    0.38
    %
    0.38
    থমে
    0.38
    etus
    0.37
     jugadores
    0.37
    POSITIVE LOGITS
     특히
    0.61
     особенно
    0.54
    특히
    0.54
    尤其
    0.53
    特に
    0.53
     especialmente
    0.52
     особливо
    0.51
     especially
    0.50
     posebno
    0.50
     özellikle
    0.50
    Act Density 0.019%

    No Known Activations