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

    Neuronpedia

    INDEX
    Explanations

    current office holders

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    统治
    0.43
    觊
    0.42
     경험
    0.40
    ンテージ
    0.39
     mediocr
    0.38
     doświad
    0.37
     শক্ত
    0.37
     sessionId
    0.36
     erau
    0.35
     popolare
    0.35
    POSITIVE LOGITS
     currently
    0.47
     Currently
    0.45
     serving
    0.45
     ২০২২
    0.44
    ডির
    0.43
     २०२२
    0.43
    Currently
    0.42
    正在
    0.42
     Current
    0.41
    न्नई
    0.41
    Act Density 0.008%

    No Known Activations