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

    Neuronpedia

    INDEX
    Explanations

    code validation and checks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     맞춰
    0.44
    抜き
    0.41
     బంగ
    0.40
     দিলেন
    0.40
     ලබා
    0.40
     заклад
    0.40
     কমিয়ে
    0.39
     ალ
    0.39
     ちゃ
    0.39
    োধনী
    0.38
    POSITIVE LOGITS
    hasClass
    0.98
    isnan
    0.95
    isempty
    0.89
     isinstance
    0.89
     !
    0.88
    isNaN
    0.86
     !(
    0.86
    isEmpty
    0.85
    startswith
    0.85
    ContainsKey
    0.85
    Act Density 0.057%

    No Known Activations