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

    Neuronpedia

    INDEX
    Explanations

    graded assignments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    er
    0.92
    ו
    0.90
    ीय
    0.86
    히
    0.82
    जरीवाल
    0.81
    추
    0.76
     धक्का
    0.74
    erin
    0.74
     diverted
    0.74
     sôi
    0.74
    POSITIVE LOGITS
    ﻓ
    1.02
     Learners
    0.96
     chaque
    0.95
     cherries
    0.94
    ிருக்கு
    0.94
     exhaustive
    0.93
    លេ
    0.91
    ЕС
    0.91
    őség
    0.91
    ্যায়
    0.90
    Act Density 0.045%

    No Known Activations