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

    Neuronpedia

    INDEX
    Explanations

    achievement and excellence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     thúc
    0.41
    💔
    0.40
    லா
    0.37
    rmi
    0.36
     coltiv
    0.36
    िला
    0.35
    埒
    0.34
    dataLayer
    0.34
    ärk
    0.33
    뿍
    0.33
    POSITIVE LOGITS
     feat
    1.95
     feats
    1.80
     accomplishment
    1.71
     achievement
    1.67
    feat
    1.42
     achievements
    1.39
     accomplishments
    1.38
     miracle
    1.37
    achievement
    1.36
    Achievement
    1.34
    Act Density 0.095%

    No Known Activations