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

    Neuronpedia

    INDEX
    Explanations

    quantifying accomplishments and contributions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     unwanted
    0.42
     offend
    0.42
     strangely
    0.41
    strange
    0.40
     strange
    0.39
     disorder
    0.39
     rudimentary
    0.39
    ப்பது
    0.38
     इच्छुक
    0.38
     shaken
    0.38
    POSITIVE LOGITS
     accomplishments
    2.06
     achievements
    1.98
     logros
    1.66
     Achievements
    1.57
    Achievements
    1.54
     accomplishment
    1.45
     achievement
    1.43
     contributions
    1.40
     successes
    1.32
    成果
    1.30
    Act Density 0.027%

    No Known Activations