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

    Neuronpedia

    INDEX
    Explanations

    mediocre, limited, medium

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Blanch
    0.39
    明明
    0.38
     allegedly
    0.37
    therefore
    0.36
    因而
    0.36
     које
    0.36
    which
    0.36
    が多く
    0.36
     incapac
    0.35
    ง่าย
    0.35
    POSITIVE LOGITS
     mediocre
    1.01
     lackluster
    1.00
     meh
    0.85
     weaker
    0.83
     lukewarm
    0.79
     underwhelming
    0.78
     mediocr
    0.77
     lesser
    0.77
     subpar
    0.76
     disappointing
    0.71
    Act Density 0.033%

    No Known Activations