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

    Neuronpedia

    INDEX
    Explanations

    Open/Closed Principle

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    യിലും
    0.48
     whirlpool
    0.45
    duction
    0.45
     экскур
    0.44
    KIA
    0.44
     اقدامات
    0.44
    ped
    0.43
    യിൽ
    0.43
     ajust
    0.43
    ConfigRequest
    0.43
    POSITIVE LOGITS
     특히
    0.43
     الوط
    0.42
     Practical
    0.40
    繹
    0.39
     paisaje
    0.38
     kuasa
    0.38
    对于
    0.38
    适用
    0.38
    اي
    0.37
     ਖ
    0.37
    Act Density 0.001%

    No Known Activations