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

    Neuronpedia

    INDEX
    Explanations

    concept of use

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     segera
    0.49
     selamat
    0.46
     kembali
    0.46
     Dewan
    0.45
    atorias
    0.44
     Badan
    0.44
     akibat
    0.43
     kejadian
    0.42
     melihat
    0.42
    дэ
    0.42
    POSITIVE LOGITS
    Concept
    0.52
    CONCEPT
    0.49
     accented
    0.48
     concept
    0.48
    コンセプト
    0.48
    SUPPORT
    0.48
    concept
    0.46
     आकर्षक
    0.46
    採用
    0.46
     应用
    0.46
    Act Density 0.004%

    No Known Activations