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

    Neuronpedia

    INDEX
    Explanations

    cross-validation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     train
    0.39
     रामचंद्र
    0.39
     गुड़
    0.38
     lockout
    0.38
     ट्रेन
    0.38
     marginRight
    0.37
    สาร
    0.37
     Bör
    0.36
     поезд
    0.36
    బో
    0.35
    POSITIVE LOGITS
    results
    0.54
     results
    0.53
    Results
    0.52
     crosses
    0.50
    CROSS
    0.50
    cross
    0.48
     averages
    0.48
     folds
    0.48
     результатов
    0.47
     Results
    0.47
    Act Density 0.003%

    No Known Activations