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

    Neuronpedia

    INDEX
    Explanations

    comparative degree

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     enorme
    0.78
     enormes
    0.69
     огромное
    0.68
     Nothing
    0.68
     niets
    0.67
     niemand
    0.67
     cualquiera
    0.67
     horrible
    0.66
     никакого
    0.65
     вси
    0.65
    POSITIVE LOGITS
     more
    3.81
    更加
    3.79
     bardziej
    3.61
     более
    3.57
     daha
    3.56
     lebih
    3.55
    更
    3.54
     더
    3.48
     більш
    3.40
     יותר
    3.36
    Act Density 2.889%

    No Known Activations