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

    Neuronpedia

    INDEX
    Explanations

    classify or categorize

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     an
    0.47
     öffentlichen
    0.46
     puncak
    0.46
     aktiv
    0.45
    sal
    0.44
     öffentliche
    0.44
     pita
    0.43
    纪录
    0.43
     anggaran
    0.43
     سواء
    0.43
    POSITIVE LOGITS
     classifying
    1.05
     classify
    0.99
     classifies
    0.96
     classifications
    0.95
     classification
    0.92
    分類
    0.88
     분류
    0.86
    classify
    0.86
     Classification
    0.83
    classification
    0.83
    Act Density 0.118%

    No Known Activations